!pip install seaborn plotly scikit-learn xgboost
import pandas as pd
from sklearn.linear_model import Ridge
import xgboost as xgb
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import plotly.express as px
from sklearn.compose import ColumnTransformer 
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV, cross_val_score, KFold
from sklearn.decomposition import PCA
from sklearn.neural_network import MLPRegressor
from sklearn.ensemble import AdaBoostRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from sklearn.metrics import mean_absolute_percentage_error 
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.ensemble import RandomForestRegressor
from sklearn.neural_network import MLPRegressor
import warnings 
warnings.filterwarnings('ignore')

Requirement already satisfied: seaborn in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (0.13.2)
Requirement already satisfied: plotly in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (6.2.0)
Requirement already satisfied: scikit-learn in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (1.7.1)
Requirement already satisfied: xgboost in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (3.0.3)
Requirement already satisfied: numpy!=1.24.0,>=1.20 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from seaborn) (2.2.4)
Requirement already satisfied: pandas>=1.2 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from seaborn) (2.2.3)
Requirement already satisfied: matplotlib!=3.6.1,>=3.4 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from seaborn) (3.10.3)
Requirement already satisfied: narwhals>=1.15.1 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from plotly) (2.0.1)
Requirement already satisfied: packaging in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from plotly) (24.2)
Requirement already satisfied: scipy>=1.8.0 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from scikit-learn) (1.16.1)
Requirement already satisfied: joblib>=1.2.0 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from scikit-learn) (1.4.2)
Requirement already satisfied: threadpoolctl>=3.1.0 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from scikit-learn) (3.6.0)
Requirement already satisfied: contourpy>=1.0.1 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.3.3)
Requirement already satisfied: cycler>=0.10 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (4.59.0)
Requirement already satisfied: kiwisolver>=1.3.1 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.4.8)
Requirement already satisfied: pillow>=8 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (10.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (3.2.3)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from pandas>=1.2->seaborn) (2025.2)
Requirement already satisfied: tzdata>=2022.7 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from pandas>=1.2->seaborn) (2025.2)
Requirement already satisfied: six>=1.5 in c:\users\admin\appdata\local\programs\python\python313\lib\site-packages (from python-dateutil>=2.7->matplotlib!=3.6.1,>=3.4->seaborn) (1.17.0)

[notice] A new release of pip is available: 24.3.1 -> 25.2
[notice] To update, run: C:\Users\Admin\AppData\Local\Programs\Python\Python313\python.exe -m pip install --upgrade pip

data = pd.read_csv(r"C:\Users\Admin\OneDrive\Escritorio\ML_Bancolombia_Leader_Test\Punto_1\restaurants_dataset.csv")
print(f"Dimensión del dataset: {data.shape}  (filas, columnas)\n")
print("Tipos de datos por columna:\n", data.dtypes, "\n")
data.head()

Dimensión del dataset: (3493, 34)  (filas, columnas)

Tipos de datos por columna:
 Registration Number                int64
Annual Turnover                    int64
Cuisine                           object
City                              object
Restaurant Location               object
Opening Day of Restaurant         object
Facebook Popularity Quotient     float64
Endorsed By                       object
Instagram Popularity Quotient    float64
Fire Audit                         int64
Liquor License Obtained            int64
Situated in a Multi Complex        int64
Dedicated Parking                  int64
Open Sitting Available             int64
Resturant Tier                   float64
Restaurant Type                   object
Restaurant Theme                  object
Restaurant Zomato Rating           int64
Restaurant City Tier               int64
Order Wait Time                    int64
Staff Responsivness                int64
Value for Money                    int64
Hygiene Rating                     int64
Food Rating                        int64
Overall Restaurant Rating        float64
Live Music Rating                float64
Comedy Gigs Rating               float64
Value Deals Rating               float64
Live Sports Rating               float64
Ambience                         float64
Lively                             int64
Service                            int64
Comfortablility                    int64
Privacy                            int64
dtype: object

missing_pct = data.isnull().mean() * 100
missing_pct = missing_pct[missing_pct > 0].sort_values(ascending=False)

# Mostrar tabla de porcentajes de nulos
print("Porcentaje de valores nulos por columna:\n")
display(missing_pct.to_frame(name='% Nulos'))

# Gráfico de barras
plt.figure(figsize=(8, 5))
sns.barplot(
    x=missing_pct.values,
    y=missing_pct.index,
    palette="viridis"
)
plt.title("Porcentaje de valores nulos por columna")
plt.xlabel("% de valores faltantes")
plt.ylabel("Columnas con nulos")
plt.tight_layout()
plt.show()

Porcentaje de valores nulos por columna:

num_cols = data.select_dtypes(include=['int64','float64']).columns.tolist()
print("Estadísticas descriptivas de variables numéricas:\n")
display(data[num_cols].describe().T)

Estadísticas descriptivas de variables numéricas:

plt.figure(figsize=(14, 4))

plt.subplot(1, 3, 1)
sns.histplot(data['Annual Turnover'], kde=True)
plt.title("Distribución de Facturación Anual")
plt.xlabel("Annual Turnover")

plt.subplot(1, 3, 2)
sns.histplot(data['Instagram Popularity Quotient'], kde=True, color='coral')
plt.title("Distribución de Popularidad en Instagram")
plt.xlabel("Instagram Popularity Quotient")

plt.subplot(1, 3, 3)
sns.histplot(data['Facebook Popularity Quotient'], kde=True, color='seagreen')
plt.title("Distribución de Popularidad en Facebook")
plt.xlabel("Facebook Popularity Quotient")

plt.tight_layout()
plt.show()

plt.figure(figsize=(14, 4))

plt.subplot(1, 5, 1)
sns.histplot(data['Ambience'], kde=True)
plt.title("Distribución de Ambiente")
plt.xlabel("Ambience")

plt.subplot(1, 5, 2)
sns.histplot(data['Lively'], kde=True, color='coral')
plt.title("Distribución de Lively")
plt.xlabel("Lively")

plt.subplot(1, 5, 3)
sns.histplot(data['Service'], kde=True, color='seagreen')
plt.title("Distribución de Service")
plt.xlabel("Service")

plt.subplot(1, 5, 4)
sns.histplot(data['Comfortablility'], kde=True, color='green')
plt.title("Distribución de Comfortablility")
plt.xlabel("Comfortablility")

plt.subplot(1, 5, 5)
sns.histplot(data['Privacy'], kde=True, color='yellow')
plt.title("Distribución de Privacy")
plt.xlabel("Privacy")

plt.tight_layout()
plt.show()

data['Live Sports Rating_missing'] = data['Live Sports Rating'].fillna(data['Live Sports Rating'].median())
data['Value Deals Rating_missing'] = data['Value Deals Rating'].fillna(data['Value Deals Rating'].median())
data['Comedy Gigs Rating_missing'] = data['Comedy Gigs Rating'].fillna(data['Comedy Gigs Rating'].median())
data['Live Music Rating_missing'] = data['Live Music Rating'].fillna(data['Live Music Rating'].median())

from matplotlib.ticker import FuncFormatter
def millions(x, pos):
    """Formatea el tick x como '10M', '50M', etc."""
    return f'{int(x/1e6)}M'
    
metrics = ['Live Music Rating','Live Sports Rating', 'Value Deals Rating', 'Comedy Gigs Rating']
colors = ['#264653', '#2a9d8f', '#e9c46a', '#e9c46a']

plt.figure(figsize=(15, 5))

for i, (metric, color) in enumerate(zip(metrics, colors), 1):
    ax = plt.subplot(2, 2, i)
    sns.boxplot(
        data=data,
        x=metric,
        y='Annual Turnover',
        color=color
    )
    ax.set_yscale('log')
    ax.yaxis.set_major_formatter(FuncFormatter(millions))
    ax.set_xlabel(metric)
    if i == 1:
        ax.set_ylabel('Annual Turnover')
    else:
        ax.set_ylabel('')
    ax.set_title(f'Turnover vs {metric}')

plt.suptitle('Facturación Anual según Ratings', y=1.02)
plt.tight_layout()
plt.show()

import plotly.io as pio
pio.renderers.default = "notebook" 
top_cities = data['City'].value_counts().nlargest(20).reset_index()
top_cities.columns = ['City', 'Count']
fig1 = px.bar(
    top_cities,
    x='Count',
    y='City',
    orientation='h',
    title='Top 20 Ciudades con más Restaurantes',
    labels={'Count': 'Cantidad de Restaurantes', 'City': 'Ciudad'}
)
fig1.update_layout(
    yaxis=dict(categoryorder='total ascending'),
    margin=dict(l=100, r=20, t=50, b=50)
)
fig1.show()

group = (
    data
    .groupby(['City', 'Cuisine'])['Annual Turnover']
    .sum()
    .reset_index()
)

top_cities = (
    data
    .groupby('City')['Annual Turnover']
    .sum()
    .nlargest(10)
    .index
)

group_top = group[group['City'].isin(top_cities)]

pivot = (
    group_top
    .pivot(index='City', columns='Cuisine', values='Annual Turnover')
    .fillna(0)
    .loc[top_cities]
)

plt.figure(figsize=(12, 8))
pivot.plot(
    kind='barh',
    stacked=True,
    width=0.8,
    figsize=(12,8),
    legend=True
)

plt.title('Facturación Anual por Ciudad y Tipo de Cocina\n(Top 10 Ciudades)')
plt.xlabel('Facturación Anual')
plt.ylabel('Ciudad')
plt.gca().invert_yaxis()

plt.legend(
    title='Cocina',
    bbox_to_anchor=(1.02, 1),
    loc='upper left'
)

plt.tight_layout()
plt.show()

<Figure size 1200x800 with 0 Axes>

freq_df = (
    data['City']
    .value_counts()
    .rename_axis('value')
    .reset_index(name='count')
)
freq_df[freq_df['count']>20]

prop = pd.crosstab(
    data['Resturant Tier'],
    data['Endorsed By'],
    normalize='index'
)

plt.figure(figsize=(10,6))
prop.plot(
    kind='bar',
    stacked=True,
    width=0.8,
    figsize=(10,6)
)

plt.title('Proporción de Endorsed by por Restaurant Tier')
plt.xlabel('Restaurant Tier')
plt.ylabel('Proporción (100%)')
plt.legend(
    title='Endorsed by',
    bbox_to_anchor=(1.02,1),
    loc='upper left'
)
plt.xticks(rotation=0)
plt.tight_layout()
plt.show()

<Figure size 1000x600 with 0 Axes>

plt.figure(figsize=(6, 4))
sns.countplot(
    data=data,
    y='Restaurant Location',
    order=data['Restaurant Location'].value_counts().index,
    palette='viridis'
)
plt.title('Número de Restaurantes por Ubicación')
plt.xlabel('Cantidad de Restaurantes')
plt.ylabel('Ubicación')
plt.tight_layout()
plt.show()

num_cols = data.select_dtypes(include=['int64','float64']).columns.tolist()
if 'Registration Number' in num_cols:
    num_cols.remove('Registration Number')

corr = data[num_cols].corr()

mask = np.triu(np.ones_like(corr, dtype=bool))

plt.figure(figsize=(12, 10))
sns.heatmap(
    corr,
    mask=mask,
    cmap='coolwarm',
    annot=True,
    fmt=".2f",
    linewidths=0.5,
    cbar_kws={"shrink": .7},
    square=True
)
plt.title('Matriz de Correlación de Variables Numéricas')
plt.tight_layout()
plt.show()

from matplotlib.ticker import FuncFormatter
def millions(x, pos):
    """Formatea el tick x como '10M', '50M', etc."""
    return f'{int(x/1e6)}M'

plt.figure(figsize=(8, 5))
ax = sns.boxplot(
    data=data,
    x='Restaurant Location',
    y='Annual Turnover',
    palette=['#2a9d8f','#e76f51']
)

ax.set_yscale('log')
ax.yaxis.set_major_formatter(FuncFormatter(millions))

plt.title('Distribución de Facturación Anual por Ubicación')
plt.xlabel('Ubicación del Restaurante')
plt.ylabel('Annual Turnover')
plt.tight_layout()
plt.show()

plt.figure(figsize=(8, 5))
sns.regplot(
    data=data,
    x='Instagram Popularity Quotient',
    y='Annual Turnover',
    scatter_kws={'alpha':0.4, 's':30},
    line_kws={'color':'crimson'}
)
plt.yscale('log') 
plt.title('Relación entre Popularidad en Instagram y Facturación Anual')
plt.xlabel('Instagram Popularity Quotient')
plt.ylabel('Annual Turnover (escala log)')
plt.tight_layout()
plt.show()

metrics = ['Staff Responsivness', 'Value for Money', 'Hygiene Rating']
colors = ['#264653', '#2a9d8f', '#e9c46a']

plt.figure(figsize=(15, 5))

for i, (metric, color) in enumerate(zip(metrics, colors), 1):
    ax = plt.subplot(1, 3, i)
    sns.boxplot(
        data=data,
        x=metric,
        y='Annual Turnover',
        color=color  # aquí asignamos el color directamente
    )
    ax.set_yscale('log')
    ax.yaxis.set_major_formatter(FuncFormatter(millions))
    ax.set_xlabel(metric)
    if i == 1:
        ax.set_ylabel('Annual Turnover')
    else:
        ax.set_ylabel('')
    ax.set_title(f'Turnover vs {metric}')

plt.suptitle('Facturación Anual según Staff, Valor y Higiene', y=1.02)
plt.tight_layout()
plt.show()

plt.figure(figsize=(12, 5))

# Resturant Tier
ax1 = plt.subplot(1, 2, 1)
sns.boxplot(
    data=data,
    x='Resturant Tier',
    y='Annual Turnover',
    palette='Set2'
)
ax1.set_yscale('log')
ax1.yaxis.set_major_formatter(FuncFormatter(millions))
ax1.set_title('Turnover vs Resturant Tier')
ax1.set_xlabel('Resturant Tier')
ax1.set_ylabel('Annual Turnover')

Text(0, 0.5, 'Annual Turnover')

means = data.groupby('Resturant Tier')['Annual Turnover'].mean()

ax = means.plot(
    kind='bar',
    logy=True,
    figsize=(6, 4),
    color=['#2a9d8f', '#e76f51']
)

ax.yaxis.set_major_formatter(lambda x, _: f"{int(x/1e6)}M")

plt.title('Media de Facturación Anual por Resturant Tier')
plt.xlabel('Resturant Tier')
plt.ylabel('Media Annual Turnover')
plt.tight_layout()
plt.show()

def fmt_millions(x, pos):
    return f'{int(x/1e6)}M'

plt.figure(figsize=(14, 5))

plt.subplot(1, 2, 1)
sns.regplot(
    data=data,
    x='Restaurant Zomato Rating',
    y='Annual Turnover',
    scatter_kws={'alpha':0.4, 's':30},
    line_kws={'color':'teal'}
)
plt.yscale('log')
plt.gca().yaxis.set_major_formatter(FuncFormatter(fmt_millions))
plt.title('Turnover vs Zomato Rating (log scale)')
plt.xlabel('Restaurant Zomato Rating')
plt.ylabel('Annual Turnover')

Text(0, 0.5, 'Annual Turnover')

plt.subplot(1, 2, 2)
sns.boxplot(
    data=data,
    x='Restaurant Zomato Rating',
    y='Annual Turnover',
    color='lightcoral'
)
plt.yscale('log')
plt.gca().yaxis.set_major_formatter(FuncFormatter(fmt_millions))
plt.title('Distribución de Turnover por Zomato Rating')
plt.xlabel('Restaurant Zomato Rating')
plt.ylabel('')

plt.tight_layout()
plt.show()

plt.figure(figsize=(8, 5))
ax = sns.violinplot(
    data=data,
    x='Endorsed By',
    y='Annual Turnover',
    order=['Not Specific', 'Tier A Celebrity', 'Local Celebrity'],
    palette=['lightgray','skyblue','salmon'],
    scale='count',
    inner='quartile',
)
ax.set_yscale('log')
ax.yaxis.set_major_formatter(FuncFormatter(fmt_millions))
ax.set_title('Distribución de Turnover por Endorsed By')
ax.set_xlabel('Endorsed By')
ax.set_ylabel('Annual Turnover')
plt.tight_layout()
plt.show()

data_copy = data.copy()
cuisine_dummies = data_copy['Cuisine'].str.get_dummies(sep=',')
df_c = pd.concat([data_copy, cuisine_dummies], axis=1)
df_c['Num_Cuisines'] = data_copy['Cuisine'].str.count(',').fillna(0).astype(int) + 1
top_cuisines = cuisine_dummies.sum().sort_values(ascending=False).head(10)
print("Top 10 cocinas más frecuentes:")
display(top_cuisines.to_frame(name='Count'))
plt.figure(figsize=(8, 5))
sns.barplot(
    x=top_cuisines.values,
    y=top_cuisines.index,
    palette='magma'
)
plt.title('Top 10 Cocinas más Comunes')
plt.xlabel('Número de Restaurantes')
plt.ylabel('Cuisine')
plt.tight_layout()
plt.show()

Top 10 cocinas más frecuentes:

cuisine_cols = cuisine_dummies.columns.tolist()
mean_turnover_by_cuisine = {
    cuisine: df_c.loc[df_c[cuisine] == 1, 'Annual Turnover'].mean()
    for cuisine in cuisine_cols
}
mean_turnover_by_cuisine = pd.Series(mean_turnover_by_cuisine).sort_values(ascending=False)

top10_avg = mean_turnover_by_cuisine.head(25)
print("Top cocinas por facturación anual promedio:")
display(top10_avg.to_frame(name='Avg Annual Turnover'))

plt.figure(figsize=(8, 6))
sns.barplot(
    x=top10_avg.values,
    y=top10_avg.index,
    palette='viridis'
)
plt.title('Top Cocinas según Facturación Anual Promedio')
plt.xlabel('Facturación Anual Promedio')
plt.ylabel('Tipo de Cocina')
plt.gca().xaxis.set_major_formatter(FuncFormatter(fmt_millions))
plt.tight_layout()
plt.show()

Top cocinas por facturación anual promedio:

data['Registration Date'] = pd.to_datetime(data['Opening Day of Restaurant'])
data['Years_Open'] = (pd.Timestamp.today() - data['Registration Date']).dt.days / 365

sns.scatterplot(data=data, x='Years_Open', y='Annual Turnover', alpha=0.5)

<Axes: xlabel='Years_Open', ylabel='Annual Turnover'>

data['Age_Bin'] = pd.cut(data['Years_Open'], bins=range(0, 35, 10), right=False)
plt.figure(figsize=(8,5))
sns.boxplot(
    data=data,
    x='Age_Bin',
    y='Annual Turnover',
    color='slateblue'
)
plt.yscale('log')
plt.gca().yaxis.set_major_formatter(FuncFormatter(lambda x, _: f"{int(x/1e6)}M"))
plt.xticks(rotation=45)
plt.xlabel('Rango de años abiertos')
plt.ylabel('Annual Turnover')
plt.title('Turnover por rango de antigüedad (Years Open)')
plt.tight_layout()
plt.show()

plt.figure(figsize=(8, 6))

data.boxplot(
    column='Years_Open',
    by='Resturant Tier',
    grid=True,
    showfliers=True,
    patch_artist=True
)

plt.title('Distribución de Años de Funcionamiento por Restaurant Tier')
plt.suptitle('')
plt.xlabel('Restaurant Tier')
plt.ylabel('Years Open')

plt.tight_layout()
plt.show()

<Figure size 800x600 with 0 Axes>

df_dic = data.select_dtypes(include=['int64', 'float64']).loc[:, lambda x: x.nunique() < 3]

datos_apilados = []
for col in df_dic.columns:
    conteos = df_dic[col].value_counts().sort_index()
    datos_apilados.append({
        'Variable': col,
        'Valor_0': conteos.get(0, 0),
        'Valor_1': conteos.get(1, 0),
        'Valor_2': conteos.get(2, 0)

    })

plot_data = pd.DataFrame(datos_apilados)
fig, ax = plt.subplots(figsize=(12, 6))
x_pos = range(len(plot_data))

bars1 = ax.bar(x_pos, plot_data['Valor_0'], label='Valor 0', color='lightcoral', alpha=0.8)
bars2 = ax.bar(x_pos, plot_data['Valor_1'], bottom=plot_data['Valor_0'],
                label='Valor 1', color='lightblue', alpha=0.8)
bars3 = ax.bar(x_pos, plot_data['Valor_2'],
                bottom=plot_data['Valor_0'] + plot_data['Valor_1'],
                label='Valor 2', color='lightgreen', alpha=0.8)

ax.set_ylabel('Cantidad de Observaciones')

ax.set_title('Distribución de Variables Dicotómicas (0, 1, 2)')

ax.set_xticks(x_pos)

ax.set_xticklabels(plot_data['Variable'], rotation=45, ha='right')

ax.legend()

ax.grid(True, alpha=0.3, axis='y')

plt.figure(figsize=(8,5))
sns.boxplot(
    data=data,
    x='Liquor License Obtained',
    y='Annual Turnover',
    color='slateblue'
)
plt.yscale('log')
plt.gca().yaxis.set_major_formatter(FuncFormatter(lambda x, _: f"{int(x/1e6)}M"))
plt.xticks(rotation=45)
plt.xlabel('Lincencia de licor')
plt.ylabel('Annual Turnover')
plt.title('Turnover por licencia de años')
plt.tight_layout()
plt.show()

plt.figure(figsize=(8,5))
sns.boxplot(
    data=data,
    x='Restaurant Type',
    y='Annual Turnover',
    color='slateblue'
)
plt.yscale('log')
plt.gca().yaxis.set_major_formatter(FuncFormatter(lambda x, _: f"{int(x/1e6)}M"))
plt.xticks(rotation=45)
plt.xlabel('Tipo de restaurantes')
plt.ylabel('Annual Turnover')
plt.title('Turnover por tipo de restaurante')
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

means = (
    data
    .groupby('Endorsed By')['Annual Turnover']
    .mean()
    .reindex(['Not Specific','Tier A Celebrity','Local Celebrity'])
)

fig, ax = plt.subplots(figsize=(6,5))

colors = ['#4da6ff', '#ff8080', '#80ff80']

bars = ax.bar(
    means.index,
    means.values,
    color=colors,
    edgecolor='none'
)

for bar in bars:
    height = bar.get_height()
    ax.text(
        bar.get_x() + bar.get_width()/2, 
        height + height*0.01,             
        f"{height:.0f}",                   
        ha='center',
        va='bottom',
        fontsize=10
    )

ax.set_title('Average Turnover by Endorsement Type')
ax.set_ylabel('Mean Annual Turnover')
ax.set_ylim(0, means.max() * 1.1) 
ax.grid(axis='y', linestyle='--', alpha=0.5)

plt.tight_layout()
plt.show()

data_def = data.drop(columns=['Live Sports Rating','Value Deals Rating','Comedy Gigs Rating','Live Music Rating'])

from scipy.stats import shapiro

stat, p_value = shapiro(data['Annual Turnover'])

print(f"Shapiro-Wilk statistic: {stat:.4f}")
print(f"p-value: {p_value:.4f}")

Shapiro-Wilk statistic: 0.6232
p-value: 0.0000

data_def['Annual Turnover Log'] = np.log1p(data_def['Annual Turnover'])

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Live Sports Rating_missing": "Live_Sports_Rating_missing"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Live_Sports_Rating_missing",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.004
Model:                             OLS   Adj. R-squared:                  0.004
Method:                  Least Squares   F-statistic:                     14.07
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           0.000179
Time:                         15:51:11   Log-Likelihood:                -2842.1
No. Observations:                 3493   AIC:                             5688.
Df Residuals:                     3491   BIC:                             5701.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
==============================================================================================
                                 coef    std err          t      P>|t|      [0.025      0.975]
----------------------------------------------------------------------------------------------
Intercept                     16.5119      0.154    107.352      0.000      16.210      16.814
Live_Sports_Rating_missing     0.1449      0.039      3.751      0.000       0.069       0.221
==============================================================================
Omnibus:                       78.289   Durbin-Watson:                   1.981
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              164.973
Skew:                          -0.085   Prob(JB):                     1.50e-36
Kurtosis:                       4.051   Cond. No.                         70.5
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Value_Deals_Rating_missing",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.012
Model:                             OLS   Adj. R-squared:                  0.011
Method:                  Least Squares   F-statistic:                     40.82
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           1.89e-10
Time:                         11:35:01   Log-Likelihood:                -2828.8
No. Observations:                 3493   AIC:                             5662.
Df Residuals:                     3491   BIC:                             5674.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
==============================================================================================
                                 coef    std err          t      P>|t|      [0.025      0.975]
----------------------------------------------------------------------------------------------
Intercept                     16.6106      0.075    220.696      0.000      16.463      16.758
Value_Deals_Rating_missing     0.1217      0.019      6.389      0.000       0.084       0.159
==============================================================================
Omnibus:                       81.265   Durbin-Watson:                   1.988
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              172.336
Skew:                          -0.095   Prob(JB):                     3.78e-38
Kurtosis:                       4.072   Cond. No.                         34.4
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Live Music Rating_missing": "Live_Music_Rating_missing"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Live_Music_Rating_missing",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.048
Model:                             OLS   Adj. R-squared:                  0.047
Method:                  Least Squares   F-statistic:                     174.4
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           6.75e-39
Time:                         11:35:37   Log-Likelihood:                -2764.0
No. Observations:                 3493   AIC:                             5532.
Df Residuals:                     3491   BIC:                             5544.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
=============================================================================================
                                coef    std err          t      P>|t|      [0.025      0.975]
---------------------------------------------------------------------------------------------
Intercept                    16.5512      0.042    397.579      0.000      16.470      16.633
Live_Music_Rating_missing     0.1338      0.010     13.207      0.000       0.114       0.154
==============================================================================
Omnibus:                      110.629   Durbin-Watson:                   1.991
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              287.144
Skew:                          -0.071   Prob(JB):                     4.44e-63
Kurtosis:                       4.397   Cond. No.                         20.0
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

data_def = data_def.drop(columns=['Comedy Gigs Rating_missing'])

data_def = data_def.drop(columns=['Opening Day of Restaurant','Registration Date','Age_Bin'])

data_def = data_def.drop(columns=['Registration Number'])

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Hygiene_Rating",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.110
Model:                             OLS   Adj. R-squared:                  0.109
Method:                  Least Squares   F-statistic:                     430.0
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           3.63e-90
Time:                         11:36:56   Log-Likelihood:                -2646.3
No. Observations:                 3493   AIC:                             5297.
Df Residuals:                     3491   BIC:                             5309.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
==================================================================================
                     coef    std err          t      P>|t|      [0.025      0.975]
----------------------------------------------------------------------------------
Intercept         16.4173      0.033    490.096      0.000      16.352      16.483
Hygiene_Rating     0.1438      0.007     20.736      0.000       0.130       0.157
==============================================================================
Omnibus:                      146.481   Durbin-Watson:                   1.983
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              468.318
Skew:                           0.042   Prob(JB):                    2.02e-102
Kurtosis:                       4.792   Cond. No.                         19.3
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Staff Responsivness": "Staff_Responsivness"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Staff_Responsivness",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.055
Model:                             OLS   Adj. R-squared:                  0.055
Method:                  Least Squares   F-statistic:                     204.5
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           4.04e-45
Time:                         11:37:39   Log-Likelihood:                -2749.7
No. Observations:                 3493   AIC:                             5503.
Df Residuals:                     3491   BIC:                             5516.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
=======================================================================================
                          coef    std err          t      P>|t|      [0.025      0.975]
---------------------------------------------------------------------------------------
Intercept              16.5539      0.038    430.973      0.000      16.479      16.629
Staff_Responsivness     0.1177      0.008     14.300      0.000       0.102       0.134
==============================================================================
Omnibus:                       94.066   Durbin-Watson:                   1.987
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              229.444
Skew:                          -0.020   Prob(JB):                     1.50e-50
Kurtosis:                       4.255   Cond. No.                         20.8
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Order Wait Time": "Order_Wait_Time"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Order_Wait_Time",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.000
Model:                             OLS   Adj. R-squared:                 -0.000
Method:                  Least Squares   F-statistic:                    0.3292
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):              0.566
Time:                         11:39:19   Log-Likelihood:                -2849.0
No. Observations:                 3493   AIC:                             5702.
Df Residuals:                     3491   BIC:                             5714.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
===================================================================================
                      coef    std err          t      P>|t|      [0.025      0.975]
-----------------------------------------------------------------------------------
Intercept          17.0776      0.020    848.487      0.000      17.038      17.117
Order_Wait_Time     0.0019      0.003      0.574      0.566      -0.004       0.008
==============================================================================
Omnibus:                       76.054   Durbin-Watson:                   1.982
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              155.723
Skew:                          -0.095   Prob(JB):                     1.53e-34
Kurtosis:                       4.017   Cond. No.                         13.8
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

from scipy.stats import f_oneway

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("Restaurant Type")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 8.97
P-value: 0.0000

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("Cuisine")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 13.45
P-value: 0.0000

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("Restaurant Theme")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 1.13
P-value: 0.2742

data_def['City'] = data_def['City'].replace('-1', 'Unknown')
freqs = data_def['City'].value_counts()

ciudades_freq = freqs[freqs >= 20].index

data_def['City_Reducida'] = data_def['City'].where(data_def['City'].isin(ciudades_freq), other='Other')

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("City")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 2.32
P-value: 0.0000

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating",
    "Live Music Rating_missing": "Live_Music_Rating_missing",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Staff Responsivness": "Staff_Responsivness",
    "Cuisine": "Cuisine",
    "City":"City"
})
model = smf.ols(
    "Annual_Turnover_Log ~ C(City)",
    data=data_def_test
).fit()
anova_tbl = sm.stats.anova_lm(model, typ=2)
print(anova_tbl)

              sum_sq      df         F        PR(>F)
C(City)   185.148122   296.0  2.324339  9.825746e-29
Residual  860.072071  3196.0       NaN           NaN

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("Restaurant Location")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 2.49
P-value: 0.1145

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("Endorsed By")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 22.17
P-value: 0.0000

groups = [group["Annual Turnover Log"].values for _, group in data_def.groupby("Resturant Tier")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 146.71
P-value: 0.0000

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Years_Open": "Years_Open"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Years_Open",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.014
Model:                             OLS   Adj. R-squared:                  0.014
Method:                  Least Squares   F-statistic:                     50.92
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           1.17e-12
Time:                         07:34:22   Log-Likelihood:                -2823.9
No. Observations:                 3493   AIC:                             5652.
Df Residuals:                     3491   BIC:                             5664.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
Intercept     16.5016      0.083    199.583      0.000      16.339      16.664
Years_Open     0.0374      0.005      7.136      0.000       0.027       0.048
==============================================================================
Omnibus:                       84.790   Durbin-Watson:                   1.985
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              157.987
Skew:                          -0.173   Prob(JB):                     4.94e-35
Kurtosis:                       3.983   Cond. No.                         143.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Facebook Popularity Quotient": "Facebook_Popularity_Quotient"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Facebook_Popularity_Quotient",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.070
Model:                             OLS   Adj. R-squared:                  0.069
Method:                  Least Squares   F-statistic:                     253.8
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           3.65e-55
Time:                         07:34:13   Log-Likelihood:                -2640.0
No. Observations:                 3394   AIC:                             5284.
Df Residuals:                     3392   BIC:                             5296.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
================================================================================================
                                   coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------------------------
Intercept                       15.9433      0.072    220.551      0.000      15.802      16.085
Facebook_Popularity_Quotient     0.0147      0.001     15.932      0.000       0.013       0.016
==============================================================================
Omnibus:                      124.048   Durbin-Watson:                   1.989
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              363.676
Skew:                          -0.005   Prob(JB):                     1.07e-79
Kurtosis:                       4.604   Cond. No.                         628.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Instagram Popularity Quotient": "Instagram_Popularity_Quotient"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Instagram_Popularity_Quotient",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.061
Model:                             OLS   Adj. R-squared:                  0.060
Method:                  Least Squares   F-statistic:                     221.4
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):           1.38e-48
Time:                         07:34:03   Log-Likelihood:                -2701.1
No. Observations:                 3437   AIC:                             5406.
Df Residuals:                     3435   BIC:                             5418.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
=================================================================================================
                                    coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------
Intercept                        16.1724      0.062    259.654      0.000      16.050      16.295
Instagram_Popularity_Quotient     0.0123      0.001     14.881      0.000       0.011       0.014
==============================================================================
Omnibus:                      116.285   Durbin-Watson:                   2.001
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              319.967
Skew:                          -0.048   Prob(JB):                     3.31e-70
Kurtosis:                       4.492   Cond. No.                         517.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import pandas as pd
from scipy.stats import chi2_contingency

contingency = pd.crosstab(data_def['City_Reducida'], data_def['Cuisine'])

chi2, p, dof, expected = chi2_contingency(contingency)

print(f"χ² = {chi2:.2f}, p-value = {p:.4f}, dof = {dof}")
print("Tabla esperada si fueran independientes:\n", expected)

χ² = 700.54, p-value = 0.0000, dof = 380
Tabla esperada si fueran independientes:
 [[ 10.60721443  24.53907816  13.14028056   6.33266533  42.90380762
   25.17234469  12.82364729   7.28256513  43.22044088  13.45691383
   32.29659319   3.7995992   18.20641283  18.52304609  14.56513026
  108.60521042  44.01202405  35.62124248  23.27254509  54.61923848]
 [  0.38362439   0.88748926   0.47523619   0.22902949   1.55167478
    0.91039221   0.46378471   0.26338391   1.56312625   0.48668766
    1.16805039   0.13741769   0.65845978   0.66991125   0.52676782
    3.92785571   1.59175494   1.28829087   0.84168337   1.97537933]
 [  0.40280561   0.93186373   0.498998     0.24048096   1.62925852
    0.95591182   0.48697395   0.27655311   1.64128257   0.51102204
    1.22645291   0.14428858   0.69138277   0.70340681   0.55310621
    4.1242485    1.67134269   1.35270541   0.88376754   2.0741483 ]
 [  4.68021758  10.82736902   5.79788148   2.79415975  18.93043229
   11.106785     5.65817349   3.21328371  19.07014028   5.93758946
   14.25021472   1.67649585   8.03320928   8.17291726   6.42656742
   47.91983968  19.41941025  15.71714858  10.26853707  24.09962783]
 [  0.46034927   1.06498712   0.57028342   0.27483539   1.86200973
    1.09247066   0.55654165   0.31606069   1.8757515    0.58402519
    1.40166046   0.16490123   0.79015173   0.8038935    0.63212139
    4.71342685   1.91010593   1.54594904   1.01002004   2.3704552 ]
 [  3.33753221   7.7211566    4.13455482   1.99255654  13.49957057
    7.92041225   4.034927     2.29144002  13.5991984    4.23418265
   10.16203836   1.19553392   5.72860006   5.82822788   4.58288005
   34.17234469  13.84826796  11.20813055   7.32264529  17.18580017]
 [  5.65845978  13.09046665   7.00973375   3.37818494  22.88720298
   13.42828514   6.84082451   3.88491268  23.05611222   7.178643
   17.2287432    2.02691096   9.71228171   9.88119095   7.76982537
   57.93587174  23.47838534  19.00229029  12.41482966  29.13684512]
 [  0.40280561   0.93186373   0.498998     0.24048096   1.62925852
    0.95591182   0.48697395   0.27655311   1.64128257   0.51102204
    1.22645291   0.14428858   0.69138277   0.70340681   0.55310621
    4.1242485    1.67134269   1.35270541   0.88376754   2.0741483 ]
 [  0.6905239    1.59748068   0.85542514   0.41225308   2.7930146
    1.63870598   0.83481248   0.47409104   2.81362725   0.87603779
    2.1024907    0.24735185   1.1852276    1.20584025   0.94818208
    7.07014028   2.86515889   2.31892356   1.51503006   3.55568279]
 [  1.68794732   3.90495276   2.09103922   1.00772975   6.82736902
    4.00572574   2.04065273   1.15888921   6.87775551   2.14142571
    5.1394217    0.60463785   2.89722302   2.9476095    2.31777841
   17.28256513   7.00372173   5.66847982   3.70340681   8.69166905]
 [  0.53707415   1.24248497   0.66533066   0.32064128   2.17234469
    1.2745491    0.6492986    0.36873747   2.18837675   0.68136273
    1.63527054   0.19238477   0.92184369   0.93787575   0.73747495
    5.498998     2.22845691   1.80360721   1.17835671   2.76553106]
 [  1.72630976   3.99370169   2.13856284   1.03063269   6.9825365
    4.09676496   2.08703121   1.1852276    7.03406814   2.19009447
    5.25622674   0.61837962   2.963069     3.01460063   2.3704552
   17.6753507    7.16289722   5.7973089    3.78757515   8.88920699]
 [  0.61379903   1.41998282   0.7603779    0.36644718   2.48267965
    1.45662754   0.74205554   0.42141426   2.501002     0.77870026
    1.86888062   0.21986831   1.05353564   1.071858     0.84282851
    6.28456914   2.5468079    2.06126539   1.34669339   3.16060693]
 [  0.42198683   0.97623819   0.52275981   0.25193244   1.70684226
    1.00143143   0.51016318   0.2897223    1.71943888   0.53535643
    1.28485543   0.15115946   0.72430575   0.73690238   0.5794446
    4.32064128   1.75093043   1.41711995   0.9258517    2.17291726]
 [  3.37589465   7.80990553   4.18207844   2.01545949  13.65473805
    8.01145147   4.08130547   2.31777841  13.75551102   4.28285142
   10.2788434    1.20927569   5.79444603   5.89521901   4.63555683
   34.56513026  14.00744346  11.33695963   7.40681363  17.3833381 ]
 [  6.21471514  14.37732608   7.69882622   3.7102777   25.13713141
   14.74835385   7.51331234   4.26681935  25.32264529   7.88434011
   18.92241626   2.22616662  10.66704838  10.85256227   8.53363871
   63.63126253  25.78643     20.87031205  13.63527054  32.00114515]
 [ 12.21843687  28.26653307  15.13627255   7.29458918  49.42084168
   28.99599198  14.77154309   8.38877756  49.78557114  15.501002
   37.20240481   4.37675351  20.97194389  21.33667335  16.77755511
  125.10220441  50.69739479  41.03206413  26.80761523  62.91583166]
 [  5.02547953  11.62610936   6.22559405   3.00028629  20.32693959
   11.92613799   6.07557973   3.45032923  20.47695391   6.37560836
   15.30146006   1.80017177   8.62582307   8.77583739   6.90065846
   51.45490982  20.85198969  16.87661036  11.0260521   25.87746922]
 [  7.59576295  17.57228743   9.4096765    4.53478385  30.72316061
   18.02576582   9.1829373    5.21500143  30.9498998    9.63641569
   23.12739765   2.72087031  13.03750358  13.26424277  10.43000286
   77.77154309  31.51674778  25.50815918  16.66533066  39.11251074]
 [  0.51789293   1.19811051   0.64156885   0.30918981   2.09476095
    1.22902949   0.62610936   0.35556828   2.11022044   0.65702834
    1.57686802   0.18551388   0.8889207    0.90438019   0.71113656
    5.30260521   2.14886917   1.73919267   1.13627255   2.6667621 ]
 [  0.44116805   1.02061265   0.54652161   0.26338391   1.78442599
    1.04695104   0.53335242   0.3028915    1.79759519   0.55969081
    1.34325794   0.15803035   0.75722874   0.77039794   0.60578299
    4.51703407   1.83051818   1.4815345    0.96793587   2.27168623]]

import pandas as pd
from scipy.stats import chi2_contingency

contingency = pd.crosstab(data_def['Endorsed By'], data_def['Resturant Tier'])

chi2, p, dof, expected = chi2_contingency(contingency)

print(f"χ² = {chi2:.2f}, p-value = {p:.4f}, dof = {dof}")
print("Tabla esperada si fueran independientes:\n", expected)

χ² = 106.48, p-value = 0.0000, dof = 2
Tabla esperada si fueran independientes:
 [[   2.27729384   28.72270616]
 [ 142.36759582 1795.63240418]
 [ 108.35511034 1366.64488966]]

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Instagram Popularity Quotient": "Instagram_Popularity_Quotient"
})
model = smf.ols(
    "Value_Deals_Rating_missing ~ Instagram_Popularity_Quotient",
    data=data_def_test
).fit()
print(model.summary())

                                OLS Regression Results                                
======================================================================================
Dep. Variable:     Value_Deals_Rating_missing   R-squared:                       0.004
Model:                                    OLS   Adj. R-squared:                  0.003
Method:                         Least Squares   F-statistic:                     12.27
Date:                        Sat, 02 Aug 2025   Prob (F-statistic):           0.000466
Time:                                07:33:53   Log-Likelihood:                -1870.4
No. Observations:                        3437   AIC:                             3745.
Df Residuals:                            3435   BIC:                             3757.
Df Model:                                   1                                         
Covariance Type:                    nonrobust                                         
=================================================================================================
                                    coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------
Intercept                         0.6053      0.049     12.375      0.000       0.509       0.701
Instagram_Popularity_Quotient     0.0023      0.001      3.503      0.000       0.001       0.004
==============================================================================
Omnibus:                      614.092   Durbin-Watson:                   2.010
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              990.442
Skew:                          -1.308   Prob(JB):                    8.48e-216
Kurtosis:                       2.731   Cond. No.                         517.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Liquor License Obtained": "Liquour_License_Obtained"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Liquour_License_Obtained",
    data=data_def_test
).fit()
print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.001
Model:                             OLS   Adj. R-squared:                  0.001
Method:                  Least Squares   F-statistic:                     5.016
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):             0.0252
Time:                         07:33:29   Log-Likelihood:                -2846.6
No. Observations:                 3493   AIC:                             5697.
Df Residuals:                     3491   BIC:                             5710.
Df Model:                            1                                         
Covariance Type:             nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
Intercept                   16.8978      0.085    197.881      0.000      16.730      17.065
Liquour_License_Obtained     0.1924      0.086      2.240      0.025       0.024       0.361
==============================================================================
Omnibus:                       76.538   Durbin-Watson:                   1.983
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              157.477
Skew:                          -0.094   Prob(JB):                     6.37e-35
Kurtosis:                       4.023   Cond. No.                         18.4
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Resturant Tier": "Resturant_Tier",
    "Years_Open": "Years_Open"
})
model = smf.ols(
    "Resturant_Tier ~ Years_Open",
    data=data_def_test
).fit()
print(model.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:         Resturant_Tier   R-squared:                       0.001
Model:                            OLS   Adj. R-squared:                  0.001
Method:                 Least Squares   F-statistic:                     5.119
Date:                Sat, 02 Aug 2025   Prob (F-statistic):             0.0237
Time:                        07:32:56   Log-Likelihood:                -256.74
No. Observations:                3444   AIC:                             517.5
Df Residuals:                    3442   BIC:                             529.8
Df Model:                           1                                         
Covariance Type:            nonrobust                                         
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
Intercept      2.0164      0.040     50.433      0.000       1.938       2.095
Years_Open    -0.0057      0.003     -2.263      0.024      -0.011      -0.001
==============================================================================
Omnibus:                     2251.996   Durbin-Watson:                   2.037
Prob(Omnibus):                  0.000   Jarque-Bera (JB):            16894.238
Skew:                          -3.263   Prob(JB):                         0.00
Kurtosis:                      11.669   Cond. No.                         143.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating",
    "Live Music Rating_missing": "Live_Music_Rating_missing",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Staff Responsivness": "Staff_Responsivness",
    "Cuisine": "Cuisine",
    "City":"City",
    "Years_Open":"Years_Open",
    "Restaurant Type":"Resturant_Type"
})
model = smf.ols(
    "Years_Open ~ C(Resturant_Type)",
    data=data_def_test
).fit()
anova_tbl = sm.stats.anova_lm(model, typ=2)
print(anova_tbl)

                        sum_sq      df           F        PR(>F)
C(Resturant_Type)   973.454273     3.0  115.795724  1.746768e-71
Residual           9776.935410  3489.0         NaN           NaN

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating",
    "Live Music Rating_missing": "Live_Music_Rating_missing",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Staff Responsivness": "Staff_Responsivness",
    "Cuisine": "Cuisine",
    "City":"City",
    "Years_Open":"Years_Open",
    "Restaurant Type":"Resturant_Type",
    "Liquor License Obtained": "Liquour_License_Obtained"
})
model = smf.ols(
    "Liquour_License_Obtained ~ C(Resturant_Type)",
    data=data_def_test
).fit()
anova_tbl = sm.stats.anova_lm(model, typ=2)
print(anova_tbl)

                      sum_sq      df           F         PR(>F)
C(Resturant_Type)   7.447997     3.0  261.923886  2.632551e-153
Residual           33.070755  3489.0         NaN            NaN

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Instagram Popularity Quotient": "Instagram_Popularity_Quotient",
    "Years_Open": "Years_Open"
})
model = smf.ols(
    "Instagram_Popularity_Quotient ~ Years_Open",
    data=data_def_test
).fit()
print(model.summary())

                                  OLS Regression Results                                 
=========================================================================================
Dep. Variable:     Instagram_Popularity_Quotient   R-squared:                       0.071
Model:                                       OLS   Adj. R-squared:                  0.071
Method:                            Least Squares   F-statistic:                     264.2
Date:                           Sat, 02 Aug 2025   Prob (F-statistic):           2.73e-57
Time:                                   11:56:44   Log-Likelihood:                -12972.
No. Observations:                           3437   AIC:                         2.595e+04
Df Residuals:                               3435   BIC:                         2.596e+04
Df Model:                                      1                                         
Covariance Type:                       nonrobust                                         
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
Intercept    100.5023      1.616     62.206      0.000      97.335     103.670
Years_Open    -1.6640      0.102    -16.254      0.000      -1.865      -1.463
==============================================================================
Omnibus:                      129.931   Durbin-Watson:                   1.999
Prob(Omnibus):                  0.000   Jarque-Bera (JB):               57.509
Skew:                           0.010   Prob(JB):                     3.25e-13
Kurtosis:                       2.367   Cond. No.                         142.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

groups = [group["Value Deals Rating_missing"].values for _, group in data_def.groupby("Endorsed By")]
f_val, p_val = f_oneway(*groups)

print(f"F-statistic: {f_val:.2f}")
print(f"P-value: {p_val:.4f}")

F-statistic: 5.98
P-value: 0.0026

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating",
    "Live Music Rating_missing": "Live_Music_Rating_missing",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Staff Responsivness": "Staff_Responsivness",
    "Cuisine": "Cuisine",
    "City":"City",
    "Years_Open":"Years_Open",
    "Restaurant Type":"Resturant_Type",
    "Liquor License Obtained": "Liquour_License_Obtained"
})
model = smf.ols(
    "Value_Deals_Rating_missing ~ C(Live_Music_Rating_missing)",
    data=data_def_test
).fit()
anova_tbl = sm.stats.anova_lm(model, typ=2)
print(anova_tbl)

                                  sum_sq      df           F        PR(>F)
C(Live_Music_Rating_missing)   30.117479     1.0  181.584248  2.196666e-40
Residual                      579.015644  3491.0         NaN           NaN

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating",
    "Live Music Rating_missing": "Live_Music_Rating_missing",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Staff Responsivness": "Staff_Responsivness",
    "Cuisine": "Cuisine",
    "City":"City",
    "Years_Open":"Years_Open",
    "Restaurant Type":"Resturant_Type",
    "Liquor License Obtained": "Liquour_License_Obtained",
    "Resturant Tier":"Resturant_Tier",
    
})
model = smf.ols(
    "Resturant_Tier ~ C(Live_Music_Rating_missing)",
    data=data_def_test
).fit()
anova_tbl = sm.stats.anova_lm(model, typ=2)
print(anova_tbl)

                                  sum_sq      df          F        PR(>F)
C(Live_Music_Rating_missing)    6.976709     7.0  15.057172  1.692741e-19
Residual                      227.437634  3436.0        NaN           NaN

import statsmodels.api as sm
import statsmodels.formula.api as smf
data_def_test = data_def.rename(columns={
    "Annual Turnover Log": "Annual_Turnover_Log",
    "Hygiene Rating": "Hygiene_Rating",
    "Live Music Rating_missing": "Live_Music_Rating_missing",
    "Value Deals Rating_missing": "Value_Deals_Rating_missing",
    "Staff Responsivness": "Staff_Responsivness",
    "Cuisine": "Cuisine",
    "City_Reducida":"City_Reducida",
    "Endorsed By":"Endorsed_By",
    "Resturant Tier":"Resturant_Tier",
    "Instagram Popularity Quotient": "Instagram_Popularity_Quotient",
    "Facebook Popularity Quotient": "Facebook_Popularity_Quotient",
    "Restaurant Type":"Resturant_Type",
    "Liquor License Obtained": "Liquour_License_Obtained",
    "Value for Money":"Value_for_Money"
})
model = smf.ols(
    "Annual_Turnover_Log ~ Hygiene_Rating+City_Reducida*Cuisine+Years_Open*Instagram_Popularity_Quotient+Liquour_License_Obtained*Resturant_Type+Resturant_Tier*Live_Music_Rating_missing+Endorsed_By*Value_Deals_Rating_missing",
    data=data_def_test
).fit()
print(model.summary())
anova_tbl = sm.stats.anova_lm(model, typ=2)
print(anova_tbl)

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.346
Model:                             OLS   Adj. R-squared:                  0.274
Method:                  Least Squares   F-statistic:                     4.827
Date:                 Sat, 02 Aug 2025   Prob (F-statistic):          5.33e-124
Time:                         16:41:08   Log-Likelihood:                -2052.3
No. Observations:                 3389   AIC:                             4775.
Df Residuals:                     3054   BIC:                             6828.
Df Model:                          334                                         
Covariance Type:             nonrobust                                         
=======================================================================================================================================
                                                                          coef    std err          t      P>|t|      [0.025      0.975]
---------------------------------------------------------------------------------------------------------------------------------------
Intercept                                                              12.8381      0.856     14.991      0.000      11.159      14.517
City_Reducida[T.Bhubaneswar]                                           -1.0613      0.488     -2.174      0.030      -2.019      -0.104
City_Reducida[T.Chandigarh]                                            -0.3547      0.488     -0.726      0.468      -1.312       0.603
City_Reducida[T.Chennai]                                               -0.8208      0.360     -2.281      0.023      -1.526      -0.115
City_Reducida[T.Greater Noida]                                         -0.0881      0.112     -0.788      0.431      -0.307       0.131
City_Reducida[T.Gurgaon]                                               -0.3137      0.238     -1.318      0.188      -0.780       0.153
City_Reducida[T.Hyderabad]                                             -0.2597      0.217     -1.195      0.232      -0.686       0.167
City_Reducida[T.Indore]                                                -0.4192      0.111     -3.760      0.000      -0.638      -0.201
City_Reducida[T.Jaipur]                                                -0.6117      0.360     -1.700      0.089      -1.317       0.094
City_Reducida[T.Kolkata]                                               -0.4247      0.080     -5.281      0.000      -0.582      -0.267
City_Reducida[T.Lucknow]                                               -0.8882      0.490     -1.814      0.070      -1.849       0.072
City_Reducida[T.Mumbai]                                                 0.1055      0.080      1.318      0.187      -0.051       0.262
City_Reducida[T.Mysore]                                                -0.1408      0.105     -1.335      0.182      -0.348       0.066
City_Reducida[T.Navi Mumbai]                                           -0.0697      0.128     -0.545      0.586      -0.320       0.181
City_Reducida[T.New Delhi]                                             -0.1939      0.305     -0.635      0.525      -0.792       0.405
City_Reducida[T.Noida]                                                 -0.4280      0.239     -1.791      0.073      -0.897       0.041
City_Reducida[T.Other]                                                 -0.6752      0.205     -3.296      0.001      -1.077      -0.274
City_Reducida[T.Pune]                                                  -0.3101      0.227     -1.369      0.171      -0.754       0.134
City_Reducida[T.Unknown]                                               -0.2056      0.238     -0.865      0.387      -0.672       0.261
City_Reducida[T.chennai]                                               -0.2019      0.360     -0.561      0.575      -0.907       0.503
City_Reducida[T.pune]                                                  -0.0529      0.111     -0.477      0.633      -0.270       0.164
Cuisine[T.algerian,belgian]                                            -0.2137      0.165     -1.292      0.196      -0.538       0.111
Cuisine[T.algerian,korean]                                             -0.2774      0.205     -1.352      0.176      -0.680       0.125
Cuisine[T.british,belgian]                                             -0.0729      0.217     -0.335      0.737      -0.499       0.353
Cuisine[T.british,japanese]                                            -0.2633      0.162     -1.628      0.104      -0.581       0.054
Cuisine[T.chinese,salvadorian]                                         -0.3488      0.184     -1.901      0.057      -0.709       0.011
Cuisine[T.cuban,british]                                               -0.2690      0.211     -1.274      0.203      -0.683       0.145
Cuisine[T.hawaiian,latvian]                                            -0.1843      0.305     -0.605      0.545      -0.782       0.413
Cuisine[T.indian,irish]                                                -0.1599      0.157     -1.019      0.308      -0.468       0.148
Cuisine[T.irish,belgian]                                               -0.5203      0.217     -2.393      0.017      -0.947      -0.094
Cuisine[T.japanese,thai]                                               -0.1400      0.170     -0.825      0.410      -0.473       0.193
Cuisine[T.nigerian,cajun]                                               0.4274      0.305      1.402      0.161      -0.171       1.025
Cuisine[T.peruvian,cuban]                                              -0.3606      0.186     -1.936      0.053      -0.726       0.005
Cuisine[T.polish,jewish]                                               -0.4425      0.177     -2.496      0.013      -0.790      -0.095
Cuisine[T.swedish,greek]                                               -0.4794      0.181     -2.646      0.008      -0.835      -0.124
Cuisine[T.tibetan,greek]                                               -0.1103      0.147     -0.752      0.452      -0.398       0.177
Cuisine[T.tibetan,italian]                                             -0.1407      0.159     -0.888      0.375      -0.452       0.170
Cuisine[T.turkish,nigerian]                                            -0.0941      0.160     -0.587      0.557      -0.408       0.220
Cuisine[T.turkish,sapnish]                                             -0.3372      0.178     -1.896      0.058      -0.686       0.011
Cuisine[T.welsh,thai]                                                  -0.1801      0.164     -1.101      0.271      -0.501       0.141
Resturant_Type[T.Buffet/Family Restaurant]                              0.2760      0.236      1.167      0.243      -0.188       0.740
Resturant_Type[T.Caffee]                                                4.2115      0.290     14.529      0.000       3.643       4.780
Resturant_Type[T.Gastro Bar]                                           -0.0648      0.038     -1.684      0.092      -0.140       0.011
Endorsed_By[T.Not Specific]                                            -0.2509      0.979     -0.256      0.798      -2.170       1.668
Endorsed_By[T.Tier A Celebrity]                                        -0.0006      0.980     -0.001      1.000      -1.922       1.921
City_Reducida[T.Bhubaneswar]:Cuisine[T.algerian,belgian]               -0.0423      0.681     -0.062      0.951      -1.378       1.294
City_Reducida[T.Chandigarh]:Cuisine[T.algerian,belgian]              4.189e-14   4.09e-13      0.102      0.919   -7.61e-13    8.45e-13
City_Reducida[T.Chennai]:Cuisine[T.algerian,belgian]                    0.5001      0.405      1.234      0.217      -0.295       1.295
City_Reducida[T.Greater Noida]:Cuisine[T.algerian,belgian]              0.3280      0.444      0.738      0.461      -0.543       1.199
City_Reducida[T.Gurgaon]:Cuisine[T.algerian,belgian]                    0.3519      0.290      1.215      0.225      -0.216       0.920
City_Reducida[T.Hyderabad]:Cuisine[T.algerian,belgian]                  0.1804      0.270      0.668      0.504      -0.349       0.710
City_Reducida[T.Indore]:Cuisine[T.algerian,belgian]                 -4.166e-14   1.71e-13     -0.244      0.807   -3.76e-13    2.93e-13
City_Reducida[T.Jaipur]:Cuisine[T.algerian,belgian]                    -0.2671      0.596     -0.448      0.654      -1.436       0.902
City_Reducida[T.Kolkata]:Cuisine[T.algerian,belgian]                    0.2645      0.279      0.947      0.344      -0.283       0.812
City_Reducida[T.Lucknow]:Cuisine[T.algerian,belgian]                    0.6394      0.682      0.938      0.349      -0.698       1.977
City_Reducida[T.Mumbai]:Cuisine[T.algerian,belgian]                     0.5217      0.272      1.915      0.056      -0.012       1.056
City_Reducida[T.Mysore]:Cuisine[T.algerian,belgian]                  1.743e-14   3.31e-14      0.527      0.598   -4.74e-14    8.23e-14
City_Reducida[T.Navi Mumbai]:Cuisine[T.algerian,belgian]               -1.0581      0.438     -2.416      0.016      -1.917      -0.199
City_Reducida[T.New Delhi]:Cuisine[T.algerian,belgian]                 -0.0401      0.380     -0.106      0.916      -0.784       0.704
City_Reducida[T.Noida]:Cuisine[T.algerian,belgian]                      0.3011      0.309      0.974      0.330      -0.305       0.907
City_Reducida[T.Other]:Cuisine[T.algerian,belgian]                      0.3170      0.234      1.356      0.175      -0.141       0.775
City_Reducida[T.Pune]:Cuisine[T.algerian,belgian]                       0.2124      0.320      0.664      0.507      -0.415       0.840
City_Reducida[T.Unknown]:Cuisine[T.algerian,belgian]                    0.0982      0.277      0.354      0.723      -0.445       0.642
City_Reducida[T.chennai]:Cuisine[T.algerian,belgian]                    0.2101      0.496      0.424      0.672      -0.762       1.182
City_Reducida[T.pune]:Cuisine[T.algerian,belgian]                      -0.3777      0.329     -1.150      0.250      -1.022       0.266
City_Reducida[T.Bhubaneswar]:Cuisine[T.algerian,korean]                 0.6277      0.692      0.907      0.364      -0.729       1.984
City_Reducida[T.Chandigarh]:Cuisine[T.algerian,korean]               2.331e-14   1.43e-13      0.163      0.870   -2.56e-13    3.03e-13
City_Reducida[T.Chennai]:Cuisine[T.algerian,korean]                     0.7648      0.442      1.732      0.083      -0.101       1.631
City_Reducida[T.Greater Noida]:Cuisine[T.algerian,korean]              -0.3074      0.346     -0.888      0.375      -0.986       0.371
City_Reducida[T.Gurgaon]:Cuisine[T.algerian,korean]                     0.2870      0.339      0.847      0.397      -0.378       0.952
City_Reducida[T.Hyderabad]:Cuisine[T.algerian,korean]                  -0.0769      0.291     -0.264      0.792      -0.647       0.494
City_Reducida[T.Indore]:Cuisine[T.algerian,korean]                  -1.735e-14   3.71e-14     -0.468      0.640   -9.01e-14    5.54e-14
City_Reducida[T.Jaipur]:Cuisine[T.algerian,korean]                   3.056e-14   1.61e-13      0.190      0.849   -2.85e-13    3.46e-13
City_Reducida[T.Kolkata]:Cuisine[T.algerian,korean]                    -0.0020      0.352     -0.006      0.996      -0.692       0.688
City_Reducida[T.Lucknow]:Cuisine[T.algerian,korean]                 -1.567e-14   3.49e-14     -0.449      0.653    -8.4e-14    5.27e-14
City_Reducida[T.Mumbai]:Cuisine[T.algerian,korean]                  -2.468e-14    2.3e-13     -0.107      0.915   -4.76e-13    4.27e-13
City_Reducida[T.Mysore]:Cuisine[T.algerian,korean]                     -0.2471      0.350     -0.707      0.480      -0.932       0.438
City_Reducida[T.Navi Mumbai]:Cuisine[T.algerian,korean]             -8.952e-14   3.61e-13     -0.248      0.804   -7.98e-13    6.19e-13
City_Reducida[T.New Delhi]:Cuisine[T.algerian,korean]                  -0.1058      0.434     -0.244      0.807      -0.956       0.745
City_Reducida[T.Noida]:Cuisine[T.algerian,korean]                       0.3798      0.322      1.181      0.238      -0.251       1.010
City_Reducida[T.Other]:Cuisine[T.algerian,korean]                       0.6354      0.277      2.294      0.022       0.092       1.179
City_Reducida[T.Pune]:Cuisine[T.algerian,korean]                       -0.2390      0.342     -0.699      0.485      -0.910       0.432
City_Reducida[T.Unknown]:Cuisine[T.algerian,korean]                    -0.3829      0.350     -1.093      0.274      -1.070       0.304
City_Reducida[T.chennai]:Cuisine[T.algerian,korean]                    -0.4977      0.613     -0.812      0.417      -1.700       0.705
City_Reducida[T.pune]:Cuisine[T.algerian,korean]                    -8.375e-14   3.16e-13     -0.265      0.791   -7.04e-13    5.37e-13
City_Reducida[T.Bhubaneswar]:Cuisine[T.british,belgian]                 0.4962      0.696      0.713      0.476      -0.869       1.861
City_Reducida[T.Chandigarh]:Cuisine[T.british,belgian]                2.06e-14   5.43e-14      0.379      0.704   -8.59e-14    1.27e-13
City_Reducida[T.Chennai]:Cuisine[T.british,belgian]                     0.7627      0.613      1.244      0.213      -0.439       1.964
City_Reducida[T.Greater Noida]:Cuisine[T.british,belgian]              -0.6308      0.463     -1.363      0.173      -1.538       0.277
City_Reducida[T.Gurgaon]:Cuisine[T.british,belgian]                    -0.1146      0.441     -0.260      0.795      -0.980       0.751
City_Reducida[T.Hyderabad]:Cuisine[T.british,belgian]                   0.0530      0.344      0.154      0.878      -0.622       0.728
City_Reducida[T.Indore]:Cuisine[T.british,belgian]                  -2.034e-14   9.09e-14     -0.224      0.823   -1.99e-13    1.58e-13
City_Reducida[T.Jaipur]:Cuisine[T.british,belgian]                  -8.145e-15   4.52e-14     -0.180      0.857   -9.67e-14    8.05e-14
City_Reducida[T.Kolkata]:Cuisine[T.british,belgian]                     0.3025      0.476      0.635      0.525      -0.632       1.237
City_Reducida[T.Lucknow]:Cuisine[T.british,belgian]                  9.587e-14   4.17e-13      0.230      0.818   -7.22e-13    9.13e-13
City_Reducida[T.Mumbai]:Cuisine[T.british,belgian]                    1.01e-14   7.47e-14      0.135      0.893   -1.36e-13    1.57e-13
City_Reducida[T.Mysore]:Cuisine[T.british,belgian]                   1.381e-14   1.04e-13      0.133      0.895    -1.9e-13    2.18e-13
City_Reducida[T.Navi Mumbai]:Cuisine[T.british,belgian]             -5.041e-14   2.06e-13     -0.245      0.807   -4.54e-13    3.53e-13
City_Reducida[T.New Delhi]:Cuisine[T.british,belgian]                  -0.4951      0.479     -1.034      0.301      -1.434       0.444
City_Reducida[T.Noida]:Cuisine[T.british,belgian]                       0.2549      0.373      0.684      0.494      -0.476       0.986
City_Reducida[T.Other]:Cuisine[T.british,belgian]                       0.2255      0.306      0.737      0.461      -0.374       0.825
City_Reducida[T.Pune]:Cuisine[T.british,belgian]                        0.2131      0.434      0.491      0.623      -0.637       1.063
City_Reducida[T.Unknown]:Cuisine[T.british,belgian]                     0.0450      0.372      0.121      0.904      -0.684       0.774
City_Reducida[T.chennai]:Cuisine[T.british,belgian]                  8.355e-14   3.51e-13      0.238      0.812   -6.05e-13    7.73e-13
City_Reducida[T.pune]:Cuisine[T.british,belgian]                    -1.202e-13   4.66e-13     -0.258      0.796   -1.03e-12    7.93e-13
City_Reducida[T.Bhubaneswar]:Cuisine[T.british,japanese]                0.7093      0.595      1.193      0.233      -0.457       1.875
City_Reducida[T.Chandigarh]:Cuisine[T.british,japanese]                 0.1787      0.683      0.262      0.794      -1.161       1.518
City_Reducida[T.Chennai]:Cuisine[T.british,japanese]                    0.8005      0.387      2.068      0.039       0.041       1.560
City_Reducida[T.Greater Noida]:Cuisine[T.british,japanese]          -4.372e-14   2.04e-13     -0.214      0.830   -4.44e-13    3.56e-13
City_Reducida[T.Gurgaon]:Cuisine[T.british,japanese]                    0.0805      0.271      0.297      0.767      -0.452       0.613
City_Reducida[T.Hyderabad]:Cuisine[T.british,japanese]                 -0.0508      0.253     -0.201      0.841      -0.546       0.444
City_Reducida[T.Indore]:Cuisine[T.british,japanese]                     0.4944      0.330      1.497      0.134      -0.153       1.142
City_Reducida[T.Jaipur]:Cuisine[T.british,japanese]                     0.5311      0.436      1.218      0.223      -0.324       1.386
City_Reducida[T.Kolkata]:Cuisine[T.british,japanese]                   -0.2012      0.246     -0.816      0.414      -0.684       0.282
City_Reducida[T.Lucknow]:Cuisine[T.british,japanese]                   -0.1542      0.682     -0.226      0.821      -1.491       1.182
City_Reducida[T.Mumbai]:Cuisine[T.british,japanese]                    -0.0692      0.164     -0.422      0.673      -0.391       0.253
City_Reducida[T.Mysore]:Cuisine[T.british,japanese]                    -0.1817      0.329     -0.552      0.581      -0.827       0.464
City_Reducida[T.Navi Mumbai]:Cuisine[T.british,japanese]            -5.839e-14    1.7e-13     -0.344      0.731   -3.91e-13    2.74e-13
City_Reducida[T.New Delhi]:Cuisine[T.british,japanese]                 -0.0620      0.356     -0.174      0.862      -0.759       0.635
City_Reducida[T.Noida]:Cuisine[T.british,japanese]                      0.3119      0.265      1.178      0.239      -0.207       0.831
City_Reducida[T.Other]:Cuisine[T.british,japanese]                      0.5672      0.230      2.462      0.014       0.115       1.019
City_Reducida[T.Pune]:Cuisine[T.british,japanese]                       0.4850      0.258      1.881      0.060      -0.021       0.991
City_Reducida[T.Unknown]:Cuisine[T.british,japanese]                    0.1698      0.263      0.646      0.518      -0.345       0.685
City_Reducida[T.chennai]:Cuisine[T.british,japanese]                   -0.1147      0.495     -0.232      0.817      -1.085       0.855
City_Reducida[T.pune]:Cuisine[T.british,japanese]                    2.346e-14    5.1e-14      0.460      0.646   -7.66e-14    1.23e-13
City_Reducida[T.Bhubaneswar]:Cuisine[T.chinese,salvadorian]             0.7321      0.601      1.219      0.223      -0.446       1.910
City_Reducida[T.Chandigarh]:Cuisine[T.chinese,salvadorian]           6.396e-15   6.15e-14      0.104      0.917   -1.14e-13    1.27e-13
City_Reducida[T.Chennai]:Cuisine[T.chinese,salvadorian]                 0.5774      0.412      1.400      0.162      -0.231       1.386
City_Reducida[T.Greater Noida]:Cuisine[T.chinese,salvadorian]          -0.0645      0.336     -0.192      0.848      -0.724       0.595
City_Reducida[T.Gurgaon]:Cuisine[T.chinese,salvadorian]                 0.3541      0.353      1.002      0.316      -0.339       1.047
City_Reducida[T.Hyderabad]:Cuisine[T.chinese,salvadorian]               0.4812      0.282      1.709      0.088      -0.071       1.033
City_Reducida[T.Indore]:Cuisine[T.chinese,salvadorian]                  0.0605      0.339      0.179      0.858      -0.604       0.725
City_Reducida[T.Jaipur]:Cuisine[T.chinese,salvadorian]               8.439e-15   3.25e-14      0.260      0.795   -5.53e-14    7.22e-14
City_Reducida[T.Kolkata]:Cuisine[T.chinese,salvadorian]                -0.0335      0.341     -0.098      0.922      -0.703       0.636
City_Reducida[T.Lucknow]:Cuisine[T.chinese,salvadorian]              4.074e-14   1.42e-13      0.287      0.774   -2.37e-13    3.19e-13
City_Reducida[T.Mumbai]:Cuisine[T.chinese,salvadorian]                  0.1587      0.333      0.477      0.633      -0.494       0.811
City_Reducida[T.Mysore]:Cuisine[T.chinese,salvadorian]                  0.3954      0.453      0.874      0.382      -0.492       1.283
City_Reducida[T.Navi Mumbai]:Cuisine[T.chinese,salvadorian]          4.389e-14    2.1e-13      0.209      0.834   -3.68e-13    4.56e-13
City_Reducida[T.New Delhi]:Cuisine[T.chinese,salvadorian]              -0.0937      0.354     -0.265      0.791      -0.787       0.600
City_Reducida[T.Noida]:Cuisine[T.chinese,salvadorian]                   0.0815      0.304      0.268      0.789      -0.515       0.678
City_Reducida[T.Other]:Cuisine[T.chinese,salvadorian]                   0.5402      0.246      2.194      0.028       0.057       1.023
City_Reducida[T.Pune]:Cuisine[T.chinese,salvadorian]                    0.2159      0.294      0.733      0.464      -0.361       0.793
City_Reducida[T.Unknown]:Cuisine[T.chinese,salvadorian]                -0.1055      0.284     -0.371      0.710      -0.662       0.451
City_Reducida[T.chennai]:Cuisine[T.chinese,salvadorian]                 0.2602      0.601      0.433      0.665      -0.918       1.438
City_Reducida[T.pune]:Cuisine[T.chinese,salvadorian]                    0.1071      0.450      0.238      0.812      -0.775       0.989
City_Reducida[T.Bhubaneswar]:Cuisine[T.cuban,british]                2.075e-14   5.91e-14      0.351      0.725    -9.5e-14    1.37e-13
City_Reducida[T.Chandigarh]:Cuisine[T.cuban,british]                 6.523e-15   3.64e-14      0.179      0.858   -6.49e-14     7.8e-14
City_Reducida[T.Chennai]:Cuisine[T.cuban,british]                       0.7963      0.430      1.852      0.064      -0.047       1.639
City_Reducida[T.Greater Noida]:Cuisine[T.cuban,british]              3.801e-14    1.2e-13      0.317      0.751   -1.97e-13    2.73e-13
City_Reducida[T.Gurgaon]:Cuisine[T.cuban,british]                       0.1350      0.329      0.410      0.682      -0.510       0.780
City_Reducida[T.Hyderabad]:Cuisine[T.cuban,british]                    -0.1298      0.300     -0.432      0.666      -0.719       0.459
City_Reducida[T.Indore]:Cuisine[T.cuban,british]                       -0.0734      0.468     -0.157      0.875      -0.991       0.845
City_Reducida[T.Jaipur]:Cuisine[T.cuban,british]                    -7.073e-16   3.37e-14     -0.021      0.983   -6.69e-14    6.54e-14
City_Reducida[T.Kolkata]:Cuisine[T.cuban,british]                      -0.2682      0.474     -0.566      0.571      -1.197       0.660
City_Reducida[T.Lucknow]:Cuisine[T.cuban,british]                       1.5153      0.695      2.181      0.029       0.153       2.878
City_Reducida[T.Mumbai]:Cuisine[T.cuban,british]                     1.426e-14   4.07e-14      0.351      0.726   -6.55e-14     9.4e-14
City_Reducida[T.Mysore]:Cuisine[T.cuban,british]                       -0.4208      0.462     -0.911      0.362      -1.326       0.485
City_Reducida[T.Navi Mumbai]:Cuisine[T.cuban,british]               -3.182e-15   4.44e-14     -0.072      0.943   -9.03e-14    8.39e-14
City_Reducida[T.New Delhi]:Cuisine[T.cuban,british]                     0.1334      0.476      0.280      0.780      -0.801       1.067
City_Reducida[T.Noida]:Cuisine[T.cuban,british]                         0.0914      0.330      0.277      0.782      -0.556       0.739
City_Reducida[T.Other]:Cuisine[T.cuban,british]                         0.4720      0.291      1.620      0.105      -0.099       1.043
City_Reducida[T.Pune]:Cuisine[T.cuban,british]                          0.0820      0.361      0.227      0.820      -0.626       0.790
City_Reducida[T.Unknown]:Cuisine[T.cuban,british]                       0.1675      0.311      0.538      0.591      -0.443       0.778
City_Reducida[T.chennai]:Cuisine[T.cuban,british]                    4.262e-14   1.32e-13      0.322      0.747   -2.17e-13    3.02e-13
City_Reducida[T.pune]:Cuisine[T.cuban,british]                        -4.7e-15    5.7e-14     -0.082      0.934   -1.17e-13    1.07e-13
City_Reducida[T.Bhubaneswar]:Cuisine[T.hawaiian,latvian]             6.557e-14   2.59e-13      0.254      0.800   -4.41e-13    5.73e-13
City_Reducida[T.Chandigarh]:Cuisine[T.hawaiian,latvian]                 0.5521      0.734      0.752      0.452      -0.887       1.992
City_Reducida[T.Chennai]:Cuisine[T.hawaiian,latvian]                    0.6161      0.558      1.103      0.270      -0.479       1.711
City_Reducida[T.Greater Noida]:Cuisine[T.hawaiian,latvian]           4.889e-14   1.89e-13      0.259      0.796   -3.21e-13    4.19e-13
City_Reducida[T.Gurgaon]:Cuisine[T.hawaiian,latvian]                    0.3360      0.489      0.687      0.492      -0.623       1.295
City_Reducida[T.Hyderabad]:Cuisine[T.hawaiian,latvian]               4.218e-05      0.440   9.59e-05      1.000      -0.862       0.862
City_Reducida[T.Indore]:Cuisine[T.hawaiian,latvian]                  5.517e-14   2.49e-13      0.221      0.825   -4.34e-13    5.44e-13
City_Reducida[T.Jaipur]:Cuisine[T.hawaiian,latvian]                     0.4795      0.562      0.853      0.394      -0.623       1.582
City_Reducida[T.Kolkata]:Cuisine[T.hawaiian,latvian]                 8.705e-14   3.55e-13      0.245      0.806   -6.08e-13    7.83e-13
City_Reducida[T.Lucknow]:Cuisine[T.hawaiian,latvian]                -4.566e-14   2.11e-13     -0.216      0.829    -4.6e-13    3.69e-13
City_Reducida[T.Mumbai]:Cuisine[T.hawaiian,latvian]                  5.416e-15    4.3e-14      0.126      0.900   -7.88e-14    8.97e-14
City_Reducida[T.Mysore]:Cuisine[T.hawaiian,latvian]                  5.461e-14   2.32e-13      0.236      0.814      -4e-13    5.09e-13
City_Reducida[T.Navi Mumbai]:Cuisine[T.hawaiian,latvian]             2.623e-15   7.77e-15      0.338      0.736   -1.26e-14    1.79e-14
City_Reducida[T.New Delhi]:Cuisine[T.hawaiian,latvian]                 -0.1390      0.450     -0.309      0.757      -1.021       0.743
City_Reducida[T.Noida]:Cuisine[T.hawaiian,latvian]                     -0.2696      0.489     -0.552      0.581      -1.228       0.689
City_Reducida[T.Other]:Cuisine[T.hawaiian,latvian]                      0.9903      0.370      2.679      0.007       0.265       1.715
City_Reducida[T.Pune]:Cuisine[T.hawaiian,latvian]                      -0.0543      0.444     -0.122      0.903      -0.925       0.816
City_Reducida[T.Unknown]:Cuisine[T.hawaiian,latvian]                   -0.0284      0.387     -0.074      0.941      -0.787       0.730
City_Reducida[T.chennai]:Cuisine[T.hawaiian,latvian]                -2.798e-14   1.38e-13     -0.202      0.840   -2.99e-13    2.43e-13
City_Reducida[T.pune]:Cuisine[T.hawaiian,latvian]                    -2.39e-14   1.14e-13     -0.209      0.834   -2.48e-13       2e-13
City_Reducida[T.Bhubaneswar]:Cuisine[T.indian,irish]                 1.406e-14   2.65e-14      0.530      0.596    -3.8e-14    6.61e-14
City_Reducida[T.Chandigarh]:Cuisine[T.indian,irish]                  9.366e-15   1.62e-14      0.578      0.563   -2.24e-14    4.11e-14
City_Reducida[T.Chennai]:Cuisine[T.indian,irish]                        0.5230      0.381      1.374      0.170      -0.224       1.269
City_Reducida[T.Greater Noida]:Cuisine[T.indian,irish]                  0.7336      0.445      1.647      0.100      -0.140       1.607
City_Reducida[T.Gurgaon]:Cuisine[T.indian,irish]                        0.0662      0.277      0.239      0.811      -0.477       0.609
City_Reducida[T.Hyderabad]:Cuisine[T.indian,irish]                      0.1934      0.253      0.764      0.445      -0.303       0.690
City_Reducida[T.Indore]:Cuisine[T.indian,irish]                         0.2667      0.328      0.814      0.416      -0.376       0.909
City_Reducida[T.Jaipur]:Cuisine[T.indian,irish]                         0.7280      0.595      1.225      0.221      -0.438       1.894
City_Reducida[T.Kolkata]:Cuisine[T.indian,irish]                       -0.0047      0.180     -0.026      0.979      -0.357       0.348
City_Reducida[T.Lucknow]:Cuisine[T.indian,irish]                        0.3662      0.681      0.538      0.591      -0.968       1.701
City_Reducida[T.Mumbai]:Cuisine[T.indian,irish]                        -0.0846      0.170     -0.499      0.618      -0.417       0.248
City_Reducida[T.Mysore]:Cuisine[T.indian,irish]                       8.55e-14   3.12e-13      0.274      0.784   -5.27e-13    6.98e-13
City_Reducida[T.Navi Mumbai]:Cuisine[T.indian,irish]                    0.1850      0.436      0.425      0.671      -0.669       1.039
City_Reducida[T.New Delhi]:Cuisine[T.indian,irish]                     -0.0784      0.334     -0.235      0.814      -0.733       0.576
City_Reducida[T.Noida]:Cuisine[T.indian,irish]                          0.2614      0.269      0.973      0.330      -0.265       0.788
City_Reducida[T.Other]:Cuisine[T.indian,irish]                          0.4838      0.224      2.164      0.031       0.046       0.922
City_Reducida[T.Pune]:Cuisine[T.indian,irish]                          -0.0785      0.279     -0.281      0.778      -0.626       0.469
City_Reducida[T.Unknown]:Cuisine[T.indian,irish]                        0.0778      0.265      0.294      0.769      -0.441       0.597
City_Reducida[T.chennai]:Cuisine[T.indian,irish]                       -0.5100      0.493     -1.034      0.301      -1.477       0.457
City_Reducida[T.pune]:Cuisine[T.indian,irish]                           0.6676      0.441      1.513      0.130      -0.198       1.533
City_Reducida[T.Bhubaneswar]:Cuisine[T.irish,belgian]               -2.785e-14    1.1e-13     -0.254      0.800   -2.43e-13    1.87e-13
City_Reducida[T.Chandigarh]:Cuisine[T.irish,belgian]                    0.3054      0.613      0.498      0.618      -0.896       1.507
City_Reducida[T.Chennai]:Cuisine[T.irish,belgian]                       0.8272      0.516      1.603      0.109      -0.184       1.839
City_Reducida[T.Greater Noida]:Cuisine[T.irish,belgian]                 0.3554      0.462      0.769      0.442      -0.550       1.261
City_Reducida[T.Gurgaon]:Cuisine[T.irish,belgian]                       0.4510      0.372      1.212      0.225      -0.278       1.180
City_Reducida[T.Hyderabad]:Cuisine[T.irish,belgian]                     0.1574      0.344      0.457      0.648      -0.518       0.833
City_Reducida[T.Indore]:Cuisine[T.irish,belgian]                        0.5017      0.284      1.765      0.078      -0.056       1.059
City_Reducida[T.Jaipur]:Cuisine[T.irish,belgian]                        1.3143      0.612      2.147      0.032       0.114       2.515
City_Reducida[T.Kolkata]:Cuisine[T.irish,belgian]                      -0.3254      0.476     -0.684      0.494      -1.258       0.607
City_Reducida[T.Lucknow]:Cuisine[T.irish,belgian]                       1.2671      0.583      2.172      0.030       0.123       2.411
City_Reducida[T.Mumbai]:Cuisine[T.irish,belgian]                       -0.1438      0.463     -0.310      0.756      -1.052       0.764
City_Reducida[T.Mysore]:Cuisine[T.irish,belgian]                    -4.571e-14   1.86e-13     -0.246      0.806    -4.1e-13    3.19e-13
City_Reducida[T.Navi Mumbai]:Cuisine[T.irish,belgian]                8.453e-15   2.51e-14      0.336      0.737   -4.08e-14    5.77e-14
City_Reducida[T.New Delhi]:Cuisine[T.irish,belgian]                    -0.3364      0.390     -0.863      0.388      -1.100       0.428
City_Reducida[T.Noida]:Cuisine[T.irish,belgian]                         0.0890      0.329      0.270      0.787      -0.557       0.735
City_Reducida[T.Other]:Cuisine[T.irish,belgian]                         0.5545      0.282      1.965      0.050       0.001       1.108
City_Reducida[T.Pune]:Cuisine[T.irish,belgian]                          0.2632      0.365      0.721      0.471      -0.453       0.979
City_Reducida[T.Unknown]:Cuisine[T.irish,belgian]                      -0.2224      0.329     -0.677      0.499      -0.867       0.422
City_Reducida[T.chennai]:Cuisine[T.irish,belgian]                   -1.155e-14   6.75e-14     -0.171      0.864   -1.44e-13    1.21e-13
City_Reducida[T.pune]:Cuisine[T.irish,belgian]                        -2.4e-14   9.23e-14     -0.260      0.795   -2.05e-13    1.57e-13
City_Reducida[T.Bhubaneswar]:Cuisine[T.japanese,thai]                   0.1702      0.597      0.285      0.776      -1.001       1.341
City_Reducida[T.Chandigarh]:Cuisine[T.japanese,thai]                 6.798e-14   2.64e-13      0.257      0.797    -4.5e-13    5.86e-13
City_Reducida[T.Chennai]:Cuisine[T.japanese,thai]                       0.8066      0.379      2.128      0.033       0.063       1.550
City_Reducida[T.Greater Noida]:Cuisine[T.japanese,thai]                 0.0968      0.330      0.293      0.769      -0.551       0.745
City_Reducida[T.Gurgaon]:Cuisine[T.japanese,thai]                       0.2065      0.311      0.665      0.506      -0.402       0.816
City_Reducida[T.Hyderabad]:Cuisine[T.japanese,thai]                     0.1501      0.261      0.575      0.565      -0.362       0.662
City_Reducida[T.Indore]:Cuisine[T.japanese,thai]                       -0.2221      0.450     -0.493      0.622      -1.105       0.661
City_Reducida[T.Jaipur]:Cuisine[T.japanese,thai]                        0.2484      0.497      0.500      0.617      -0.726       1.223
City_Reducida[T.Kolkata]:Cuisine[T.japanese,thai]                       0.3846      0.175      2.199      0.028       0.042       0.728
City_Reducida[T.Lucknow]:Cuisine[T.japanese,thai]                    3.176e-14   1.44e-13      0.220      0.826   -2.51e-13    3.15e-13
City_Reducida[T.Mumbai]:Cuisine[T.japanese,thai]                    -4.954e-14   2.49e-13     -0.199      0.843   -5.38e-13    4.39e-13
City_Reducida[T.Mysore]:Cuisine[T.japanese,thai]                        0.0337      0.449      0.075      0.940      -0.846       0.913
City_Reducida[T.Navi Mumbai]:Cuisine[T.japanese,thai]                1.143e-13   4.95e-13      0.231      0.817   -8.56e-13    1.08e-12
City_Reducida[T.New Delhi]:Cuisine[T.japanese,thai]                     0.3493      0.381      0.916      0.360      -0.399       1.097
City_Reducida[T.Noida]:Cuisine[T.japanese,thai]                         0.2579      0.312      0.828      0.408      -0.353       0.869
City_Reducida[T.Other]:Cuisine[T.japanese,thai]                         0.4513      0.243      1.859      0.063      -0.025       0.927
City_Reducida[T.Pune]:Cuisine[T.japanese,thai]                          0.2966      0.261      1.137      0.256      -0.215       0.808
City_Reducida[T.Unknown]:Cuisine[T.japanese,thai]                       0.2540      0.276      0.920      0.358      -0.287       0.795
City_Reducida[T.chennai]:Cuisine[T.japanese,thai]                    1.526e-14   6.63e-14      0.230      0.818   -1.15e-13    1.45e-13
City_Reducida[T.pune]:Cuisine[T.japanese,thai]                         -0.1086      0.445     -0.244      0.807      -0.982       0.764
City_Reducida[T.Bhubaneswar]:Cuisine[T.nigerian,cajun]               8.801e-15   4.12e-14      0.214      0.831    -7.2e-14    8.96e-14
City_Reducida[T.Chandigarh]:Cuisine[T.nigerian,cajun]                 1.22e-14   5.98e-14      0.204      0.838   -1.05e-13     1.3e-13
City_Reducida[T.Chennai]:Cuisine[T.nigerian,cajun]                     -0.1294      0.649     -0.199      0.842      -1.402       1.143
City_Reducida[T.Greater Noida]:Cuisine[T.nigerian,cajun]             -1.61e-14   8.52e-14     -0.189      0.850   -1.83e-13    1.51e-13
City_Reducida[T.Gurgaon]:Cuisine[T.nigerian,cajun]                     -0.7044      0.450     -1.565      0.118      -1.587       0.178
City_Reducida[T.Hyderabad]:Cuisine[T.nigerian,cajun]                   -0.1356      0.582     -0.233      0.816      -1.276       1.005
City_Reducida[T.Indore]:Cuisine[T.nigerian,cajun]                    2.487e-14   1.11e-13      0.225      0.822   -1.92e-13    2.42e-13
City_Reducida[T.Jaipur]:Cuisine[T.nigerian,cajun]                   -1.196e-14   3.17e-14     -0.377      0.706   -7.41e-14    5.02e-14
City_Reducida[T.Kolkata]:Cuisine[T.nigerian,cajun]                     -0.5809      0.411     -1.412      0.158      -1.388       0.226
City_Reducida[T.Lucknow]:Cuisine[T.nigerian,cajun]                     -0.5160      0.729     -0.708      0.479      -1.945       0.913
City_Reducida[T.Mumbai]:Cuisine[T.nigerian,cajun]                      -0.2437      0.503     -0.484      0.628      -1.230       0.743
City_Reducida[T.Mysore]:Cuisine[T.nigerian,cajun]                    8.915e-15   1.85e-14      0.481      0.630   -2.74e-14    4.52e-14
City_Reducida[T.Navi Mumbai]:Cuisine[T.nigerian,cajun]              -3.003e-16   9.29e-15     -0.032      0.974   -1.85e-14    1.79e-14
City_Reducida[T.New Delhi]:Cuisine[T.nigerian,cajun]                 1.089e-14   2.15e-14      0.507      0.612   -3.12e-14     5.3e-14
City_Reducida[T.Noida]:Cuisine[T.nigerian,cajun]                       -0.5188      0.489     -1.061      0.289      -1.478       0.440
City_Reducida[T.Other]:Cuisine[T.nigerian,cajun]                       -0.3034      0.389     -0.780      0.435      -1.066       0.459
City_Reducida[T.Pune]:Cuisine[T.nigerian,cajun]                        -0.0243      0.585     -0.041      0.967      -1.172       1.123
City_Reducida[T.Unknown]:Cuisine[T.nigerian,cajun]                   8.643e-15   2.36e-14      0.366      0.714   -3.76e-14    5.49e-14
City_Reducida[T.chennai]:Cuisine[T.nigerian,cajun]                     -0.7101      0.558     -1.272      0.204      -1.805       0.385
City_Reducida[T.pune]:Cuisine[T.nigerian,cajun]                      7.619e-15   3.54e-14      0.215      0.830   -6.18e-14    7.71e-14
City_Reducida[T.Bhubaneswar]:Cuisine[T.peruvian,cuban]               5.504e-15   1.49e-14      0.370      0.711   -2.37e-14    3.47e-14
City_Reducida[T.Chandigarh]:Cuisine[T.peruvian,cuban]               -7.601e-15   2.36e-14     -0.322      0.748   -5.39e-14    3.87e-14
City_Reducida[T.Chennai]:Cuisine[T.peruvian,cuban]                      0.6757      0.425      1.592      0.112      -0.157       1.508
City_Reducida[T.Greater Noida]:Cuisine[T.peruvian,cuban]             2.796e-14   1.21e-13      0.232      0.817   -2.09e-13    2.65e-13
City_Reducida[T.Gurgaon]:Cuisine[T.peruvian,cuban]                      0.1233      0.320      0.385      0.700      -0.504       0.751
City_Reducida[T.Hyderabad]:Cuisine[T.peruvian,cuban]                    0.0617      0.281      0.220      0.826      -0.489       0.613
City_Reducida[T.Indore]:Cuisine[T.peruvian,cuban]                      7.6e-15   4.72e-14      0.161      0.872   -8.49e-14       1e-13
City_Reducida[T.Jaipur]:Cuisine[T.peruvian,cuban]                       0.6834      0.446      1.533      0.125      -0.191       1.557
City_Reducida[T.Kolkata]:Cuisine[T.peruvian,cuban]                      0.1957      0.291      0.673      0.501      -0.375       0.766
City_Reducida[T.Lucknow]:Cuisine[T.peruvian,cuban]                  -1.812e-14   6.85e-14     -0.265      0.791   -1.52e-13    1.16e-13
City_Reducida[T.Mumbai]:Cuisine[T.peruvian,cuban]                   -1.051e-14   2.13e-14     -0.493      0.622   -5.23e-14    3.13e-14
City_Reducida[T.Mysore]:Cuisine[T.peruvian,cuban]                       0.2028      0.341      0.595      0.552      -0.466       0.872
City_Reducida[T.Navi Mumbai]:Cuisine[T.peruvian,cuban]              -2.239e-14   9.16e-14     -0.244      0.807   -2.02e-13    1.57e-13
City_Reducida[T.New Delhi]:Cuisine[T.peruvian,cuban]                   -0.3646      0.425     -0.858      0.391      -1.198       0.469
City_Reducida[T.Noida]:Cuisine[T.peruvian,cuban]                        0.3946      0.298      1.326      0.185      -0.189       0.978
City_Reducida[T.Other]:Cuisine[T.peruvian,cuban]                        0.6468      0.260      2.490      0.013       0.138       1.156
City_Reducida[T.Pune]:Cuisine[T.peruvian,cuban]                         0.6701      0.320      2.094      0.036       0.043       1.298
City_Reducida[T.Unknown]:Cuisine[T.peruvian,cuban]                     -0.0299      0.295     -0.101      0.919      -0.608       0.548
City_Reducida[T.chennai]:Cuisine[T.peruvian,cuban]                    -1.4e-14   5.14e-14     -0.272      0.785   -1.15e-13    8.68e-14
City_Reducida[T.pune]:Cuisine[T.peruvian,cuban]                        -0.1285      0.245     -0.524      0.600      -0.609       0.352
City_Reducida[T.Bhubaneswar]:Cuisine[T.polish,jewish]                   0.5767      0.684      0.843      0.399      -0.765       1.919
City_Reducida[T.Chandigarh]:Cuisine[T.polish,jewish]                -1.433e-15   6.08e-15     -0.236      0.814   -1.34e-14    1.05e-14
City_Reducida[T.Chennai]:Cuisine[T.polish,jewish]                       0.9452      0.403      2.344      0.019       0.155       1.736
City_Reducida[T.Greater Noida]:Cuisine[T.polish,jewish]                -0.2704      0.285     -0.947      0.344      -0.830       0.289
City_Reducida[T.Gurgaon]:Cuisine[T.polish,jewish]                       0.3297      0.350      0.942      0.346      -0.357       1.016
City_Reducida[T.Hyderabad]:Cuisine[T.polish,jewish]                     0.5712      0.284      2.009      0.045       0.014       1.129
City_Reducida[T.Indore]:Cuisine[T.polish,jewish]                        0.7631      0.336      2.269      0.023       0.104       1.423
City_Reducida[T.Jaipur]:Cuisine[T.polish,jewish]                        0.0807      0.599      0.135      0.893      -1.094       1.256
City_Reducida[T.Kolkata]:Cuisine[T.polish,jewish]                      -0.2692      0.461     -0.584      0.559      -1.173       0.634
City_Reducida[T.Lucknow]:Cuisine[T.polish,jewish]                    3.002e-14   1.17e-13      0.256      0.798      -2e-13     2.6e-13
City_Reducida[T.Mumbai]:Cuisine[T.polish,jewish]                        0.1730      0.279      0.620      0.535      -0.374       0.720
City_Reducida[T.Mysore]:Cuisine[T.polish,jewish]                    -3.307e-14   1.48e-13     -0.223      0.824   -3.24e-13    2.58e-13
City_Reducida[T.Navi Mumbai]:Cuisine[T.polish,jewish]                   0.4170      0.442      0.942      0.346      -0.450       1.284
City_Reducida[T.New Delhi]:Cuisine[T.polish,jewish]                     0.2879      0.462      0.623      0.534      -0.619       1.195
City_Reducida[T.Noida]:Cuisine[T.polish,jewish]                         0.6861      0.301      2.283      0.023       0.097       1.276
City_Reducida[T.Other]:Cuisine[T.polish,jewish]                         0.7280      0.253      2.878      0.004       0.232       1.224
City_Reducida[T.Pune]:Cuisine[T.polish,jewish]                          0.6076      0.287      2.115      0.035       0.044       1.171
City_Reducida[T.Unknown]:Cuisine[T.polish,jewish]                       0.3823      0.287      1.330      0.184      -0.181       0.946
City_Reducida[T.chennai]:Cuisine[T.polish,jewish]                    -4.87e-15   2.29e-14     -0.213      0.831   -4.97e-14       4e-14
City_Reducida[T.pune]:Cuisine[T.polish,jewish]                       9.075e-15   3.73e-14      0.243      0.808    -6.4e-14    8.22e-14
City_Reducida[T.Bhubaneswar]:Cuisine[T.swedish,greek]               -5.043e-15   9.08e-15     -0.556      0.579   -2.28e-14    1.28e-14
City_Reducida[T.Chandigarh]:Cuisine[T.swedish,greek]                    0.8827      0.685      1.288      0.198      -0.461       2.226
City_Reducida[T.Chennai]:Cuisine[T.swedish,greek]                       0.8813      0.444      1.986      0.047       0.011       1.751
City_Reducida[T.Greater Noida]:Cuisine[T.swedish,greek]              2.201e-15   6.82e-15      0.323      0.747   -1.12e-14    1.56e-14
City_Reducida[T.Gurgaon]:Cuisine[T.swedish,greek]                       0.4497      0.377      1.192      0.233      -0.290       1.189
City_Reducida[T.Hyderabad]:Cuisine[T.swedish,greek]                     0.2554      0.287      0.891      0.373      -0.307       0.818
City_Reducida[T.Indore]:Cuisine[T.swedish,greek]                     2.461e-15   1.23e-14      0.200      0.841   -2.16e-14    2.65e-14
City_Reducida[T.Jaipur]:Cuisine[T.swedish,greek]                    -3.222e-15   8.79e-15     -0.366      0.714   -2.05e-14     1.4e-14
City_Reducida[T.Kolkata]:Cuisine[T.swedish,greek]                      -0.3075      0.463     -0.665      0.506      -1.214       0.599
City_Reducida[T.Lucknow]:Cuisine[T.swedish,greek]                      -0.1030      0.571     -0.181      0.857      -1.222       1.016
City_Reducida[T.Mumbai]:Cuisine[T.swedish,greek]                    -9.956e-15   4.19e-14     -0.238      0.812   -9.21e-14    7.22e-14
City_Reducida[T.Mysore]:Cuisine[T.swedish,greek]                        0.5681      0.336      1.690      0.091      -0.091       1.227
City_Reducida[T.Navi Mumbai]:Cuisine[T.swedish,greek]                   0.2408      0.334      0.721      0.471      -0.414       0.895
City_Reducida[T.New Delhi]:Cuisine[T.swedish,greek]                     0.2569      0.401      0.641      0.521      -0.529       1.042
City_Reducida[T.Noida]:Cuisine[T.swedish,greek]                         0.7214      0.312      2.314      0.021       0.110       1.333
City_Reducida[T.Other]:Cuisine[T.swedish,greek]                         0.6282      0.260      2.415      0.016       0.118       1.138
City_Reducida[T.Pune]:Cuisine[T.swedish,greek]                          0.1664      0.309      0.539      0.590      -0.439       0.771
City_Reducida[T.Unknown]:Cuisine[T.swedish,greek]                       0.2262      0.302      0.749      0.454      -0.366       0.818
City_Reducida[T.chennai]:Cuisine[T.swedish,greek]                      -0.6798      0.600     -1.132      0.258      -1.857       0.498
City_Reducida[T.pune]:Cuisine[T.swedish,greek]                          0.5470      0.449      1.219      0.223      -0.333       1.427
City_Reducida[T.Bhubaneswar]:Cuisine[T.tibetan,greek]                   0.9629      0.543      1.773      0.076      -0.102       2.028
City_Reducida[T.Chandigarh]:Cuisine[T.tibetan,greek]                    0.1806      0.521      0.347      0.729      -0.841       1.202
City_Reducida[T.Chennai]:Cuisine[T.tibetan,greek]                       0.7271      0.369      1.970      0.049       0.003       1.451
City_Reducida[T.Greater Noida]:Cuisine[T.tibetan,greek]                -0.0923      0.208     -0.443      0.658      -0.501       0.316
City_Reducida[T.Gurgaon]:Cuisine[T.tibetan,greek]                       0.1584      0.256      0.618      0.536      -0.344       0.661
City_Reducida[T.Hyderabad]:Cuisine[T.tibetan,greek]                     0.1246      0.230      0.541      0.588      -0.327       0.576
City_Reducida[T.Indore]:Cuisine[T.tibetan,greek]                    -1.345e-16   1.54e-15     -0.088      0.930   -3.14e-15    2.88e-15
City_Reducida[T.Jaipur]:Cuisine[T.tibetan,greek]                        0.1351      0.452      0.299      0.765      -0.750       1.021
City_Reducida[T.Kolkata]:Cuisine[T.tibetan,greek]                       0.2050      0.139      1.478      0.140      -0.067       0.477
City_Reducida[T.Lucknow]:Cuisine[T.tibetan,greek]                      -0.0379      0.561     -0.068      0.946      -1.137       1.061
City_Reducida[T.Mumbai]:Cuisine[T.tibetan,greek]                       -0.1712      0.117     -1.457      0.145      -0.402       0.059
City_Reducida[T.Mysore]:Cuisine[T.tibetan,greek]                        0.0981      0.175      0.562      0.574      -0.245       0.441
City_Reducida[T.Navi Mumbai]:Cuisine[T.tibetan,greek]                   0.0417      0.191      0.219      0.827      -0.332       0.416
City_Reducida[T.New Delhi]:Cuisine[T.tibetan,greek]                    -0.0077      0.322     -0.024      0.981      -0.639       0.624
City_Reducida[T.Noida]:Cuisine[T.tibetan,greek]                         0.2035      0.251      0.811      0.418      -0.289       0.696
City_Reducida[T.Other]:Cuisine[T.tibetan,greek]                         0.4329      0.216      2.009      0.045       0.010       0.855
City_Reducida[T.Pune]:Cuisine[T.tibetan,greek]                          0.2017      0.237      0.850      0.395      -0.263       0.667
City_Reducida[T.Unknown]:Cuisine[T.tibetan,greek]                       0.1075      0.247      0.435      0.663      -0.377       0.592
City_Reducida[T.chennai]:Cuisine[T.tibetan,greek]                       0.2226      0.409      0.544      0.586      -0.579       1.024
City_Reducida[T.pune]:Cuisine[T.tibetan,greek]                          0.1095      0.222      0.493      0.622      -0.326       0.545
City_Reducida[T.Bhubaneswar]:Cuisine[T.tibetan,italian]                 1.1754      0.594      1.978      0.048       0.010       2.340
City_Reducida[T.Chandigarh]:Cuisine[T.tibetan,italian]                  0.2479      0.594      0.418      0.676      -0.916       1.412
City_Reducida[T.Chennai]:Cuisine[T.tibetan,italian]                     0.7369      0.381      1.936      0.053      -0.010       1.483
City_Reducida[T.Greater Noida]:Cuisine[T.tibetan,italian]                    0          0        nan        nan           0           0
City_Reducida[T.Gurgaon]:Cuisine[T.tibetan,italian]                    -0.0401      0.286     -0.140      0.888      -0.600       0.520
City_Reducida[T.Hyderabad]:Cuisine[T.tibetan,italian]                   0.0664      0.245      0.271      0.787      -0.415       0.547
City_Reducida[T.Indore]:Cuisine[T.tibetan,italian]                     -0.4901      0.446     -1.100      0.272      -1.364       0.384
City_Reducida[T.Jaipur]:Cuisine[T.tibetan,italian]                     -0.1017      0.414     -0.246      0.806      -0.913       0.709
City_Reducida[T.Kolkata]:Cuisine[T.tibetan,italian]                     0.0902      0.165      0.546      0.585      -0.234       0.414
City_Reducida[T.Lucknow]:Cuisine[T.tibetan,italian]                     0.5146      0.564      0.913      0.361      -0.591       1.620
City_Reducida[T.Mumbai]:Cuisine[T.tibetan,italian]                      0.0960      0.239      0.402      0.688      -0.372       0.564
City_Reducida[T.Mysore]:Cuisine[T.tibetan,italian]                      0.1699      0.195      0.870      0.384      -0.213       0.553
City_Reducida[T.Navi Mumbai]:Cuisine[T.tibetan,italian]                -0.1401      0.436     -0.321      0.748      -0.995       0.715
City_Reducida[T.New Delhi]:Cuisine[T.tibetan,italian]                  -0.2101      0.339     -0.619      0.536      -0.875       0.455
City_Reducida[T.Noida]:Cuisine[T.tibetan,italian]                       0.0736      0.269      0.274      0.784      -0.453       0.600
City_Reducida[T.Other]:Cuisine[T.tibetan,italian]                       0.4465      0.230      1.938      0.053      -0.005       0.898
City_Reducida[T.Pune]:Cuisine[T.tibetan,italian]                        0.1041      0.254      0.410      0.682      -0.394       0.602
City_Reducida[T.Unknown]:Cuisine[T.tibetan,italian]                    -0.1137      0.266     -0.427      0.669      -0.636       0.408
City_Reducida[T.chennai]:Cuisine[T.tibetan,italian]                     0.3716      0.594      0.626      0.532      -0.793       1.537
City_Reducida[T.pune]:Cuisine[T.tibetan,italian]                        0.1109      0.325      0.341      0.733      -0.527       0.749
City_Reducida[T.Bhubaneswar]:Cuisine[T.turkish,nigerian]                0.8577      0.680      1.261      0.207      -0.476       2.191
City_Reducida[T.Chandigarh]:Cuisine[T.turkish,nigerian]                 0.1801      0.680      0.265      0.791      -1.154       1.514
City_Reducida[T.Chennai]:Cuisine[T.turkish,nigerian]                    0.6116      0.387      1.582      0.114      -0.146       1.370
City_Reducida[T.Greater Noida]:Cuisine[T.turkish,nigerian]                   0          0        nan        nan           0           0
City_Reducida[T.Gurgaon]:Cuisine[T.turkish,nigerian]                    0.2414      0.306      0.789      0.430      -0.358       0.841
City_Reducida[T.Hyderabad]:Cuisine[T.turkish,nigerian]                  0.2803      0.267      1.051      0.293      -0.243       0.803
City_Reducida[T.Indore]:Cuisine[T.turkish,nigerian]                    -0.7667      0.447     -1.717      0.086      -1.642       0.109
City_Reducida[T.Jaipur]:Cuisine[T.turkish,nigerian]                     0.5897      0.495      1.191      0.234      -0.381       1.561
City_Reducida[T.Kolkata]:Cuisine[T.turkish,nigerian]                    0.1594      0.331      0.482      0.630      -0.489       0.808
City_Reducida[T.Lucknow]:Cuisine[T.turkish,nigerian]                         0          0        nan        nan           0           0
City_Reducida[T.Mumbai]:Cuisine[T.turkish,nigerian]                    -0.1199      0.195     -0.616      0.538      -0.502       0.262
City_Reducida[T.Mysore]:Cuisine[T.turkish,nigerian]                          0          0        nan        nan           0           0
City_Reducida[T.Navi Mumbai]:Cuisine[T.turkish,nigerian]                0.2454      0.437      0.562      0.574      -0.611       1.102
City_Reducida[T.New Delhi]:Cuisine[T.turkish,nigerian]                  0.0019      0.335      0.006      0.995      -0.656       0.660
City_Reducida[T.Noida]:Cuisine[T.turkish,nigerian]                      0.1583      0.262      0.604      0.546      -0.356       0.672
City_Reducida[T.Other]:Cuisine[T.turkish,nigerian]                      0.4131      0.232      1.780      0.075      -0.042       0.868
City_Reducida[T.Pune]:Cuisine[T.turkish,nigerian]                       0.2692      0.267      1.007      0.314      -0.255       0.794
City_Reducida[T.Unknown]:Cuisine[T.turkish,nigerian]                   -0.1699      0.267     -0.637      0.524      -0.693       0.353
City_Reducida[T.chennai]:Cuisine[T.turkish,nigerian]                   -0.3031      0.495     -0.613      0.540      -1.273       0.667
City_Reducida[T.pune]:Cuisine[T.turkish,nigerian]                            0          0        nan        nan           0           0
City_Reducida[T.Bhubaneswar]:Cuisine[T.turkish,sapnish]                      0          0        nan        nan           0           0
City_Reducida[T.Chandigarh]:Cuisine[T.turkish,sapnish]                 -0.0076      0.553     -0.014      0.989      -1.091       1.076
City_Reducida[T.Chennai]:Cuisine[T.turkish,sapnish]                     0.3439      0.411      0.838      0.402      -0.461       1.149
City_Reducida[T.Greater Noida]:Cuisine[T.turkish,sapnish]                    0          0        nan        nan           0           0
City_Reducida[T.Gurgaon]:Cuisine[T.turkish,sapnish]                     0.2565      0.334      0.767      0.443      -0.399       0.912
City_Reducida[T.Hyderabad]:Cuisine[T.turkish,sapnish]                   0.0329      0.293      0.112      0.911      -0.542       0.608
City_Reducida[T.Indore]:Cuisine[T.turkish,sapnish]                     -0.0825      0.288     -0.287      0.774      -0.647       0.481
City_Reducida[T.Jaipur]:Cuisine[T.turkish,sapnish]                      0.4671      0.599      0.779      0.436      -0.708       1.642
City_Reducida[T.Kolkata]:Cuisine[T.turkish,sapnish]                     0.4918      0.467      1.054      0.292      -0.423       1.407
City_Reducida[T.Lucknow]:Cuisine[T.turkish,sapnish]                     0.5227      0.570      0.917      0.359      -0.595       1.640
City_Reducida[T.Mumbai]:Cuisine[T.turkish,sapnish]                      0.0534      0.250      0.214      0.831      -0.437       0.543
City_Reducida[T.Mysore]:Cuisine[T.turkish,sapnish]                     -0.5524      0.451     -1.226      0.220      -1.436       0.331
City_Reducida[T.Navi Mumbai]:Cuisine[T.turkish,sapnish]                      0          0        nan        nan           0           0
City_Reducida[T.New Delhi]:Cuisine[T.turkish,sapnish]                  -0.1363      0.363     -0.375      0.708      -0.849       0.576
City_Reducida[T.Noida]:Cuisine[T.turkish,sapnish]                       0.4373      0.283      1.544      0.123      -0.118       0.993
City_Reducida[T.Other]:Cuisine[T.turkish,sapnish]                       0.3646      0.243      1.499      0.134      -0.112       0.842
City_Reducida[T.Pune]:Cuisine[T.turkish,sapnish]                        0.6259      0.316      1.983      0.047       0.007       1.245
City_Reducida[T.Unknown]:Cuisine[T.turkish,sapnish]                    -0.1824      0.294     -0.621      0.535      -0.759       0.394
City_Reducida[T.chennai]:Cuisine[T.turkish,sapnish]                    -0.4225      0.599     -0.705      0.481      -1.598       0.753
City_Reducida[T.pune]:Cuisine[T.turkish,sapnish]                        0.1266      0.334      0.379      0.704      -0.528       0.781
City_Reducida[T.Bhubaneswar]:Cuisine[T.welsh,thai]                      0.0273      0.681      0.040      0.968      -1.307       1.362
City_Reducida[T.Chandigarh]:Cuisine[T.welsh,thai]                       0.3236      0.685      0.472      0.637      -1.021       1.668
City_Reducida[T.Chennai]:Cuisine[T.welsh,thai]                          0.6579      0.384      1.713      0.087      -0.095       1.411
City_Reducida[T.Greater Noida]:Cuisine[T.welsh,thai]                   -0.2365      0.250     -0.946      0.344      -0.727       0.254
City_Reducida[T.Gurgaon]:Cuisine[T.welsh,thai]                          0.1503      0.282      0.534      0.594      -0.402       0.702
City_Reducida[T.Hyderabad]:Cuisine[T.welsh,thai]                        0.0045      0.250      0.018      0.986      -0.485       0.494
City_Reducida[T.Indore]:Cuisine[T.welsh,thai]                          -0.8708      0.447     -1.948      0.052      -1.747       0.006
City_Reducida[T.Jaipur]:Cuisine[T.welsh,thai]                           0.1406      0.416      0.338      0.735      -0.674       0.956
City_Reducida[T.Kolkata]:Cuisine[T.welsh,thai]                         -0.5258      0.179     -2.940      0.003      -0.876      -0.175
City_Reducida[T.Lucknow]:Cuisine[T.welsh,thai]                          0.2075      0.532      0.390      0.697      -0.836       1.251
City_Reducida[T.Mumbai]:Cuisine[T.welsh,thai]                          -0.0650      0.188     -0.347      0.729      -0.433       0.303
City_Reducida[T.Mysore]:Cuisine[T.welsh,thai]                          -0.2068      0.328     -0.630      0.529      -0.851       0.437
City_Reducida[T.Navi Mumbai]:Cuisine[T.welsh,thai]                     -0.0012      0.236     -0.005      0.996      -0.464       0.462
City_Reducida[T.New Delhi]:Cuisine[T.welsh,thai]                       -0.1328      0.327     -0.406      0.685      -0.774       0.508
City_Reducida[T.Noida]:Cuisine[T.welsh,thai]                            0.2206      0.265      0.833      0.405      -0.298       0.740
City_Reducida[T.Other]:Cuisine[T.welsh,thai]                            0.2230      0.228      0.979      0.328      -0.224       0.670
City_Reducida[T.Pune]:Cuisine[T.welsh,thai]                             0.0915      0.265      0.345      0.730      -0.428       0.611
City_Reducida[T.Unknown]:Cuisine[T.welsh,thai]                         -0.2861      0.261     -1.095      0.273      -0.798       0.226
City_Reducida[T.chennai]:Cuisine[T.welsh,thai]                         -0.4450      0.495     -0.898      0.369      -1.416       0.526
City_Reducida[T.pune]:Cuisine[T.welsh,thai]                            -1.1067      0.327     -3.381      0.001      -1.749      -0.465
Hygiene_Rating                                                          0.0787      0.008     10.067      0.000       0.063       0.094
Years_Open                                                             -0.0032      0.030     -0.107      0.915      -0.061       0.055
Instagram_Popularity_Quotient                                          -0.0045      0.006     -0.696      0.486      -0.017       0.008
Years_Open:Instagram_Popularity_Quotient                                0.0009      0.000      2.108      0.035       6e-05       0.002
Liquour_License_Obtained                                                4.3173      0.287     15.056      0.000       3.755       4.880
Liquour_License_Obtained:Resturant_Type[T.Buffet/Family Restaurant]     0.2760      0.236      1.167      0.243      -0.188       0.740
Liquour_License_Obtained:Resturant_Type[T.Caffee]                      -4.3093      0.289    -14.906      0.000      -4.876      -3.742
Liquour_License_Obtained:Resturant_Type[T.Gastro Bar]                  -0.0648      0.038     -1.684      0.092      -0.140       0.011
Resturant_Tier                                                         -0.4323      0.160     -2.710      0.007      -0.745      -0.120
Live_Music_Rating_missing                                              -0.0391      0.068     -0.579      0.563      -0.171       0.093
Resturant_Tier:Live_Music_Rating_missing                                0.0473      0.035      1.353      0.176      -0.021       0.116
Value_Deals_Rating_missing                                              0.0064      0.247      0.026      0.979      -0.478       0.491
Endorsed_By[T.Not Specific]:Value_Deals_Rating_missing                  0.0361      0.248      0.146      0.884      -0.450       0.523
Endorsed_By[T.Tier A Celebrity]:Value_Deals_Rating_missing             -0.0125      0.249     -0.050      0.960      -0.500       0.475
==============================================================================
Omnibus:                      218.525   Durbin-Watson:                   2.041
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              991.151
Skew:                           0.074   Prob(JB):                    5.95e-216
Kurtosis:                       5.645   Cond. No.                     7.86e+19
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The smallest eigenvalue is 7.62e-31. This might indicate that there are
strong multicollinearity problems or that the design matrix is singular.
                                              sum_sq      df           F  \
City_Reducida                             -73.025518    20.0  -16.738603   
Cuisine                                    22.470394    19.0    5.421652   
Resturant_Type                              0.745436     3.0    1.139104   
Endorsed_By                                 2.392316     2.0    5.483567   
City_Reducida:Cuisine                     116.943371   380.0    1.410804   
Hygiene_Rating                             22.107875     1.0  101.349484   
Years_Open                                 26.350417     1.0  120.798638   
Instagram_Popularity_Quotient              21.286172     1.0   97.582538   
Years_Open:Instagram_Popularity_Quotient    0.968915     1.0    4.441812   
Liquour_License_Obtained                    1.712197     1.0    7.849252   
Liquour_License_Obtained:Resturant_Type    49.129520     3.0   75.075083   
Resturant_Tier                              9.019409     1.0   41.347822   
Live_Music_Rating_missing                   5.283550     1.0   24.221463   
Resturant_Tier:Live_Music_Rating_missing    0.399265     1.0    1.830357   
Value_Deals_Rating_missing                  0.294460     1.0    1.349897   
Endorsed_By:Value_Deals_Rating_missing      0.413173     2.0    0.947058   
Residual                                  666.184436  3054.0         NaN   

                                                PR(>F)  
City_Reducida                             1.000000e+00  
Cuisine                                   2.753396e-13  
Resturant_Type                            3.202416e-01  
Endorsed_By                               4.195491e-03  
City_Reducida:Cuisine                     1.655090e-05  
Hygiene_Rating                            1.784145e-23  
Years_Open                                1.380936e-27  
Instagram_Popularity_Quotient             1.125691e-22  
Years_Open:Instagram_Popularity_Quotient  3.515032e-02  
Liquour_License_Obtained                  5.116203e-03  
Liquour_License_Obtained:Resturant_Type   7.535881e-47  
Resturant_Tier                            1.473473e-10  
Live_Music_Rating_missing                 9.042276e-07  
Resturant_Tier:Live_Music_Rating_missing  1.761856e-01  
Value_Deals_Rating_missing                2.453869e-01  
Endorsed_By:Value_Deals_Rating_missing    3.879945e-01  
Residual                                           NaN

C:\Users\Admin\AppData\Local\Programs\Python\Python313\Lib\site-packages\statsmodels\base\model.py:1894: ValueWarning:

covariance of constraints does not have full rank. The number of constraints is 3, but rank is 2

C:\Users\Admin\AppData\Local\Programs\Python\Python313\Lib\site-packages\statsmodels\base\model.py:1894: ValueWarning:

covariance of constraints does not have full rank. The number of constraints is 380, but rank is 286

import statsmodels.formula.api as smf
df = data_def.rename(columns={
    'Fire Audit': 'Fire_Audit',
    'Liquor License Obtained': 'Liquor_License_Obtained',
    'Annual Turnover Log': 'Annual_Turnover_Log'
})

model = smf.ols(
    'Annual_Turnover_Log ~ Liquor_License_Obtained * Fire_Audit',
    data=df
).fit()

print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.003
Model:                             OLS   Adj. R-squared:                  0.002
Method:                  Least Squares   F-statistic:                     3.047
Date:                 Fri, 01 Aug 2025   Prob (F-statistic):             0.0276
Time:                         16:48:20   Log-Likelihood:                -2844.6
No. Observations:                 3493   AIC:                             5697.
Df Residuals:                     3489   BIC:                             5722.
Df Model:                            3                                         
Covariance Type:             nonrobust                                         
======================================================================================================
                                         coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------------------------------
Intercept                             16.9987      0.165    103.140      0.000      16.676      17.322
Liquor_License_Obtained                0.0572      0.166      0.345      0.730      -0.268       0.383
Fire_Audit                            -0.1379      0.193     -0.716      0.474      -0.516       0.240
Liquor_License_Obtained:Fire_Audit     0.1813      0.194      0.934      0.350      -0.199       0.562
==============================================================================
Omnibus:                       77.063   Durbin-Watson:                   1.984
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              158.643
Skew:                          -0.096   Prob(JB):                     3.56e-35
Kurtosis:                       4.026   Cond. No.                         68.6
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.formula.api as smf
df = data_def.rename(columns={
    'Situated in a Multi Complex': 'Situated_in_a_Multi_Complex',
    'Dedicated Parking': 'Dedicated_Parking',
    'Annual Turnover Log': 'Annual_Turnover_Log'
})

model = smf.ols(
    'Annual_Turnover_Log ~ Situated_in_a_Multi_Complex * Dedicated_Parking',
    data=df
).fit()

print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.002
Model:                             OLS   Adj. R-squared:                  0.002
Method:                  Least Squares   F-statistic:                     2.884
Date:                 Fri, 01 Aug 2025   Prob (F-statistic):             0.0344
Time:                         16:49:35   Log-Likelihood:                -2844.8
No. Observations:                 3493   AIC:                             5698.
Df Residuals:                     3489   BIC:                             5722.
Df Model:                            3                                         
Covariance Type:             nonrobust                                         
=================================================================================================================
                                                    coef    std err          t      P>|t|      [0.025      0.975]
-----------------------------------------------------------------------------------------------------------------
Intercept                                        17.0638      0.047    362.683      0.000      16.972      17.156
Situated_in_a_Multi_Complex                      -0.0186      0.052     -0.355      0.723      -0.121       0.084
Dedicated_Parking                                 0.0769      0.053      1.460      0.144      -0.026       0.180
Situated_in_a_Multi_Complex:Dedicated_Parking    -0.0347      0.059     -0.592      0.554      -0.150       0.080
==============================================================================
Omnibus:                       72.968   Durbin-Watson:                   1.983
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              145.344
Skew:                          -0.100   Prob(JB):                     2.75e-32
Kurtosis:                       3.979   Cond. No.                         18.6
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

import statsmodels.formula.api as smf
df = data_def.rename(columns={
    'Food Rating': 'Food_Rating',
    'Service': 'Service',
    'Annual Turnover Log': 'Annual_Turnover_Log'
})

model = smf.ols(
    'Annual_Turnover_Log ~ Food_Rating * Service',
    data=df
).fit()

print(model.summary())

                             OLS Regression Results                            
===============================================================================
Dep. Variable:     Annual_Turnover_Log   R-squared:                       0.000
Model:                             OLS   Adj. R-squared:                 -0.001
Method:                  Least Squares   F-statistic:                    0.3113
Date:                 Fri, 01 Aug 2025   Prob (F-statistic):              0.817
Time:                         16:49:53   Log-Likelihood:                -2848.7
No. Observations:                 3493   AIC:                             5705.
Df Residuals:                     3489   BIC:                             5730.
Df Model:                            3                                         
Covariance Type:             nonrobust                                         
=======================================================================================
                          coef    std err          t      P>|t|      [0.025      0.975]
---------------------------------------------------------------------------------------
Intercept              17.1741      0.109    157.326      0.000      16.960      17.388
Food_Rating            -0.0096      0.014     -0.679      0.497      -0.037       0.018
Service                -0.0192      0.022     -0.862      0.389      -0.063       0.024
Food_Rating:Service     0.0021      0.003      0.744      0.457      -0.003       0.008
==============================================================================
Omnibus:                       77.061   Durbin-Watson:                   1.982
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              158.033
Skew:                          -0.099   Prob(JB):                     4.83e-35
Kurtosis:                       4.023   Cond. No.                         473.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

def categorizar_valor(x):
    if x in [1, 2, 3]:
        return 'Bajo'
    elif x in [4, 5]:
        return 'Medio'
    elif x in [6, 7, 8]:
        return 'Alto'
    else:
        return None

data_def['Liquor License Obtained Cat'] = data_def['Liquor License Obtained'].map({1: 'Si', 0: 'No'})
data_def['Value Deals Rating_missing Cat'] = data_def['Value Deals Rating_missing'].apply(categorizar_valor)

data_def['city_cuisine']=data_def['City_Reducida']+"_"+data_def['Cuisine']
data_def['popularity_years']=data_def['Instagram Popularity Quotient']*data_def['Years_Open']
data_def['tier_music']=data_def['Resturant Tier']*data_def['Live Music Rating_missing']
data_def['liquor_type']=data_def['Liquor License Obtained Cat']+"_"+data_def['Restaurant Type']
data_def['values_endorsed']=data_def['Endorsed By']+"_"+data_def['Value Deals Rating_missing Cat']

data_def = data_def[['Annual Turnover Log','Hygiene Rating','City_Reducida','Cuisine','city_cuisine','Years_Open','Instagram Popularity Quotient','popularity_years','Liquor License Obtained Cat','Restaurant Type','liquor_type','Resturant Tier','Live Music Rating_missing','tier_music','Endorsed By','Value Deals Rating_missing Cat','values_endorsed']]

data_def['Instagram Popularity Quotient'] = data_def['Instagram Popularity Quotient'].fillna(data_def['Instagram Popularity Quotient'].median())
data_def['popularity_years'] = data_def['popularity_years'].fillna(data_def['popularity_years'].median())
data_def['Resturant Tier'] = data_def['Resturant Tier'].fillna(data_def['Resturant Tier'].median())
data_def['tier_music'] = data_def['tier_music'].fillna(data_def['tier_music'].median())

catCol = data_def.select_dtypes(include= ['object'] ).columns.to_list()
numCol = data_def.select_dtypes(include= ['float64','int64'] ).columns.to_list()

preprocesador = ColumnTransformer([('onehot', OneHotEncoder(handle_unknown = 'ignore'),catCol)],remainder = 'passthrough')


datospre =preprocesador.fit_transform(data_def)

codCat=preprocesador.named_transformers_['onehot'].get_feature_names_out(catCol)
labels = np.concatenate([codCat,numCol])

datosProc = pd.DataFrame(datospre.toarray(), columns=labels)

df_med=datosProc
Q1 = df_med['Annual Turnover Log'].quantile(0.25)
Q3 = df_med['Annual Turnover Log'].quantile(0.75)
IQR = Q3 - Q1

lower_bound = Q1 - 1.5 * IQR
upper_bound = Q3 + 1.5 * IQR

filtered_data = df_med[(df_med['Annual Turnover Log'] >= lower_bound) & (df_med['Annual Turnover Log'] <= upper_bound)]

print(f"Filtrados: {filtered_data.shape[0]} filas (sin outliers)")

Filtrados: 3436 filas (sin outliers)

x=filtered_data.drop(columns=['Annual Turnover Log'])
y=filtered_data[['Annual Turnover Log']]

xEntrenamiento, xPrueba, yEntrenamiento, yPrueba = train_test_split(x,y,train_size=0.7, random_state=123)

from sklearn.model_selection import GridSearchCV, KFold
from sklearn.metrics import (
    mean_squared_error,
    mean_absolute_error,
    r2_score,
    mean_absolute_percentage_error
)
import pandas as pd

def run_grid_search(
    X_train, y_train,
    X_test=None, y_test=None,
    estimator=None,
    param_grid=None,
    cv_splits=5,
    metrics=None,
    random_state=42,
    n_jobs=-1,
    verbose=0
):
    if metrics is None:
        metrics = [
            'neg_mean_squared_error',
            'neg_mean_absolute_error',
            'r2',
            'neg_mean_absolute_percentage_error'
        ]

    scoring = {m: m for m in metrics}
    refit_metric = metrics[0]

    inner_cv = KFold(n_splits=cv_splits, shuffle=True, random_state=random_state)

    grid = GridSearchCV(
        estimator=estimator,
        param_grid=param_grid,
        scoring=scoring,
        cv=inner_cv,
        refit=refit_metric,
        return_train_score=False,
        n_jobs=n_jobs,
        verbose=verbose
    )
    grid.fit(X_train, y_train)

    # Convertimos cv_results_ en DataFrame y "desnegativizamos"
    df = pd.DataFrame(grid.cv_results_)
    for m in metrics:
        col = f"mean_test_{m}"
        # Si era mape (negativo) o any neg_, lo revertimos y renombramos
        if m.startswith('neg_'):
            name = m.replace('neg_', '')
            df[f"mean_test_{name}"] = -df[col]
        else:
            df[f"mean_test_{m}"] = df[col]

    results = {
        'best_estimator': grid.best_estimator_,
        'best_params':    grid.best_params_,
        'cv_results_df':  df
    }

    # Predicciones en train
    y_train_pred = grid.best_estimator_.predict(X_train)
    results['train_scores'] = {
        'mse': mean_squared_error(y_train, y_train_pred),
        'mae': mean_absolute_error(y_train, y_train_pred),
        'r2':  r2_score(y_train, y_train_pred),
        'mape': mean_absolute_percentage_error(y_train, y_train_pred)
    }

    # Predicciones en test (si se provee)
    if X_test is not None and y_test is not None:
        y_test_pred = grid.best_estimator_.predict(X_test)
        results['test_scores'] = {
            'mse': mean_squared_error(y_test, y_test_pred),
            'mae': mean_absolute_error(y_test, y_test_pred),
            'r2':  r2_score(y_test, y_test_pred),
            'mape': mean_absolute_percentage_error(y_test, y_test_pred)
        }

    return results

ridge = Ridge()
param_grid = {
    'alpha': [0.01, 0.1, 1.0, 10.0, 100.0],
    'fit_intercept': [True, False]
}


results = run_grid_search(
    xEntrenamiento, yEntrenamiento,
    xPrueba, yPrueba,
    estimator=ridge,
    param_grid=param_grid,
    cv_splits=5,
    metrics=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2','neg_mean_absolute_percentage_error'],
    verbose=1
)

print("Mejores parámetros:", results['best_params'])
print("Métricas en entrenamiento:", results['train_scores'])
print("Métricas en prueba:", results['test_scores'])

Fitting 5 folds for each of 10 candidates, totalling 50 fits
Mejores parámetros: {'alpha': 100.0, 'fit_intercept': True}
Métricas en entrenamiento: {'mse': 0.17636010747782754, 'mae': 0.3305633488317981, 'r2': 0.2996276389933501, 'mape': 0.019476920294949726}
Métricas en prueba: {'mse': 0.18057752081411288, 'mae': 0.3390956918508284, 'r2': 0.27037822479784723, 'mape': 0.019929175499234633}

lr = LinearRegression()
param_grid_lr = {
    'fit_intercept': [True, False],
    'copy_X':        [True, False],
    'positive':      [False, True], 
    'tol':           [1e-6, 1e-4, 1e-2] 
}
results_lr = run_grid_search(
    xEntrenamiento, yEntrenamiento,
    X_test=xPrueba, y_test=yPrueba,
    estimator=lr,
    param_grid=param_grid_lr,
    cv_splits=5,
    metrics=['neg_mean_squared_error','neg_mean_absolute_error','r2','neg_mean_absolute_percentage_error'],
    verbose=1
)
print("Mejores parámetros LR:", results_lr['best_params'])
print("Train scores:", results_lr['train_scores'])
print("Test  scores:", results_lr['test_scores'])

Fitting 5 folds for each of 24 candidates, totalling 120 fits
Mejores parámetros LR: {'copy_X': True, 'fit_intercept': True, 'positive': False, 'tol': 1e-06}
Train scores: {'mse': 0.15197310863979677, 'mae': 0.3003089325411634, 'r2': 0.39647482398503175, 'mape': 0.01766871584954887}
Test  scores: {'mse': 0.20276154539115934, 'mae': 0.3535110486610771, 'r2': 0.18074388205097414, 'mape': 0.02077405901428926}

xgb_model = xgb.XGBRegressor(
    objective='reg:squarederror',
    random_state=42,
    n_jobs=-1,
    verbosity=0
)

param_grid_xgb = {
    'n_estimators':      [100, 300],
    'max_depth':         [3, 5, 7],
    'learning_rate':     [0.01, 0.05, 0.1],
    'reg_alpha':         [0.1, 1.0],
    'reg_lambda':        [1.0, 5.0]
}

results_xgb = run_grid_search(
    xEntrenamiento, yEntrenamiento,
    X_test=xPrueba, y_test=yPrueba,
    estimator=xgb_model,
    param_grid=param_grid_xgb,
    cv_splits=5,
    metrics=['neg_mean_squared_error','neg_mean_absolute_error','r2','neg_mean_absolute_percentage_error'],
    verbose=1
)

print("Mejores parámetros XGB:", results_xgb['best_params'])
print("Train scores:", results_xgb['train_scores'])
print("Test  scores:", results_xgb['test_scores'])

Fitting 5 folds for each of 72 candidates, totalling 360 fits
Mejores parámetros XGB: {'learning_rate': 0.05, 'max_depth': 3, 'n_estimators': 300, 'reg_alpha': 1.0, 'reg_lambda': 5.0}
Train scores: {'mse': 0.15002329647541046, 'mae': 0.30378881096839905, 'r2': 0.40421807765960693, 'mape': 0.017894936725497246}
Test  scores: {'mse': 0.17858749628067017, 'mae': 0.3348684012889862, 'r2': 0.27841895818710327, 'mape': 0.019669145345687866}

ada_model = AdaBoostRegressor(
    random_state=42
)
param_grid_ada = {
    'n_estimators':      [50, 100],
    'learning_rate':     [0.01, 0.1, 0.5, 1.0],
    'loss':              ['linear', 'square', 'exponential']
}
results_ada = run_grid_search(
    xEntrenamiento, yEntrenamiento,
    X_test=xPrueba, y_test=yPrueba,
    estimator=ada_model,
    param_grid=param_grid_ada,
    cv_splits=5,
    metrics=['neg_mean_squared_error','neg_mean_absolute_error','r2','neg_mean_absolute_percentage_error'],
    verbose=1
)

print("Mejores parámetros AdaBoost:", results_ada['best_params'])
print("Train scores:", results_ada['train_scores'])
print("Test  scores:", results_ada['test_scores'])

Fitting 5 folds for each of 24 candidates, totalling 120 fits
Mejores parámetros AdaBoost: {'learning_rate': 0.1, 'loss': 'linear', 'n_estimators': 50}
Train scores: {'mse': 0.19472923541976003, 'mae': 0.35479893564680326, 'r2': 0.22667900174021194, 'mape': 0.020874243888165972}
Test  scores: {'mse': 0.19962382022404196, 'mae': 0.3618164819170651, 'r2': 0.1934218310902973, 'mape': 0.021224991608803208}

rf_model = RandomForestRegressor(random_state=42)

param_grid_rf = {
    'n_estimators':      [100, 200, 500],
    'max_depth':         [None, 10, 20],
    'min_samples_split': [2, 5, 10],
    'max_features':      ['auto', 'sqrt']
}

results_rf = run_grid_search(
    xEntrenamiento, yEntrenamiento,
    X_test=xPrueba, y_test=yPrueba,
    estimator=rf_model,
    param_grid=param_grid_rf,
    cv_splits=5,
    metrics=[
        'neg_mean_squared_error',
        'neg_mean_absolute_error',
        'r2',
        'neg_mean_absolute_percentage_error'
    ],
    verbose=1
)

print("Mejores parámetros Random Forest:", results_rf['best_params'])
print("Train scores:", results_rf['train_scores'])
print("Test  scores:", results_rf['test_scores'])

Fitting 5 folds for each of 54 candidates, totalling 270 fits
Mejores parámetros Random Forest: {'max_depth': None, 'max_features': 'sqrt', 'min_samples_split': 10, 'n_estimators': 500}
Train scores: {'mse': 0.08513670294764214, 'mae': 0.2286458507790223, 'r2': 0.6618997657434607, 'mape': 0.013473102652427574}
Test  scores: {'mse': 0.18120873630053536, 'mae': 0.3341117541575857, 'r2': 0.2678278045591468, 'mape': 0.019640572424019304}

import numpy as np
import matplotlib.pyplot as plt
from statsmodels.stats.diagnostic import het_breuschpagan
import statsmodels.api as sm

y_true_orig = pd.Series(
   yPrueba.iloc[:, 0],
    index=yPrueba.index
)

y_pred = results['best_estimator'].predict(xPrueba)
y_pred_orig = pd.Series(
   y_pred,  
    index=yPrueba.index
)

resid_orig = y_true_orig - y_pred_orig

plt.figure(figsize=(8,5))
plt.scatter(y_pred_orig, resid_orig, alpha=0.6)
plt.axhline(0, color='red', linewidth=1.5, linestyle='--')
plt.xlabel('Valores predichos')
plt.ylabel('Residuos')
plt.title('Residuos vs Predicciones')
plt.tight_layout()
plt.show()

plt.figure(figsize=(8, 4))
plt.boxplot(resid_orig, vert=False, patch_artist=True,
            boxprops=dict(facecolor='lightgray', color='black'),
            medianprops=dict(color='red'),
            flierprops=dict(marker='o', markerfacecolor='black', markersize=5))
plt.title('Evaluate the distribution of residuals for Normality')
plt.xlabel('Residuales')
plt.yticks([])
plt.show()

import statsmodels.api as sm

resid = resid_orig
plt.figure(figsize=(6,6))
sm.qqplot(resid, line='45', fit=True, alpha=0.6)
plt.title("QQ-plot de residuos")
plt.tight_layout()
plt.show()

<Figure size 600x600 with 0 Axes>

y_pred = results['best_estimator'].predict(xPrueba)

import matplotlib.pyplot as plt
import seaborn as sns

plt.figure(figsize=(10, 6))

sns.scatterplot(
    x=range(len(yPrueba)), 
    y=yPrueba['Annual Turnover Log'], 
    label='Real', 
    color='blue', 
    alpha=0.5
)

sns.scatterplot(
    x=range(len(y_pred)), 
    y=y_pred.ravel(), 
    label='Predicho (Ridge)', 
    color='orange', 
    alpha=0.6
)

plt.title("Comparación de puntos: Turnover real vs predicho")
plt.xlabel("Índice")
plt.ylabel("Annual Turnover Log")
plt.legend()
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from statsmodels.stats.diagnostic import het_breuschpagan
import statsmodels.api as sm

y_true_orig = pd.Series(
   yPrueba.iloc[:, 0],
    index=yPrueba.index
)

y_pred = results_xgb['best_estimator'].predict(xPrueba)
y_pred_orig = pd.Series(
   y_pred,  
    index=yPrueba.index
)

resid_orig = y_true_orig - y_pred_orig

plt.figure(figsize=(8,5))
plt.scatter(y_pred_orig, resid_orig, alpha=0.6)
plt.axhline(0, color='red', linewidth=1.5, linestyle='--')
plt.xlabel('Valores predichos')
plt.ylabel('Residuos')
plt.title('Residuos vs Predicciones')
plt.tight_layout()
plt.show()

plt.figure(figsize=(8, 4))
plt.boxplot(resid_orig, vert=False, patch_artist=True,
            boxprops=dict(facecolor='lightgray', color='black'),
            medianprops=dict(color='red'),
            flierprops=dict(marker='o', markerfacecolor='black', markersize=5))
plt.title('Evaluate the distribution of residuals for Normality')
plt.xlabel('Residuales')
plt.yticks([])
plt.show()

import statsmodels.api as sm

resid = resid_orig

plt.figure(figsize=(6,6))
sm.qqplot(resid, line='45', fit=True, alpha=0.6)
plt.title("QQ-plot de residuos")
plt.tight_layout()
plt.show()

<Figure size 600x600 with 0 Axes>

y_pred = results_xgb['best_estimator'].predict(xPrueba)

import matplotlib.pyplot as plt
import seaborn as sns

plt.figure(figsize=(10, 6))

sns.scatterplot(
    x=range(len(yPrueba)), 
    y=yPrueba['Annual Turnover Log'], 
    label='Real', 
    color='blue', 
    alpha=0.5
)

sns.scatterplot(
    x=range(len(y_pred)), 
    y=y_pred.ravel(), 
    label='Predicho (XGBoost)', 
    color='orange', 
    alpha=0.6
)

plt.title("Comparación de puntos: Turnover real vs predicho")
plt.xlabel("Índice")
plt.ylabel("Annual Turnover Log")
plt.legend()
plt.show()

	count	mean	std	min	25%	50%	75%	max
Registration Number	3493.0	6.174700e+04	1.008487e+03	60001.0	60874.0	61747.00	6.262000e+04	6.349300e+04
Annual Turnover	3493.0	3.072571e+07	2.165125e+07	3500000.0	18000000.0	30000000.00	3.700000e+07	4.000000e+08
Facebook Popularity Quotient	3394.0	7.793872e+01	9.829169e+00	43.0	72.0	79.00	8.574500e+01	9.776000e+01
Instagram Popularity Quotient	3437.0	7.440468e+01	1.094033e+01	40.0	66.0	74.05	8.240000e+01	9.870000e+01
Fire Audit	3493.0	7.887203e-01	4.082748e-01	0.0	1.0	1.00	1.000000e+00	1.000000e+00
Liquor License Obtained	3493.0	9.882622e-01	1.077187e-01	0.0	1.0	1.00	1.000000e+00	1.000000e+00
Situated in a Multi Complex	3493.0	8.081878e-01	3.937825e-01	0.0	1.0	1.00	1.000000e+00	1.000000e+00
Dedicated Parking	3493.0	8.018895e-01	3.986329e-01	0.0	1.0	1.00	1.000000e+00	1.000000e+00
Open Sitting Available	3493.0	8.001718e-01	3.999284e-01	0.0	1.0	1.00	1.000000e+00	1.000000e+00
Resturant Tier	3444.0	1.926539e+00	2.609297e-01	1.0	2.0	2.00	2.000000e+00	2.000000e+00
Restaurant Zomato Rating	3493.0	2.696536e+00	7.872713e-01	0.0	2.0	3.00	3.000000e+00	5.000000e+00
Restaurant City Tier	3493.0	3.014601e-01	4.589577e-01	0.0	0.0	0.00	1.000000e+00	1.000000e+00
Order Wait Time	3493.0	5.509591e+00	2.854476e+00	1.0	3.0	5.00	8.000000e+00	1.000000e+01
Staff Responsivness	3493.0	4.538506e+00	1.093832e+00	1.0	4.0	5.00	5.000000e+00	8.000000e+00
Value for Money	3493.0	4.526482e+00	9.139370e-01	1.0	4.0	5.00	5.000000e+00	7.000000e+00
Hygiene Rating	3493.0	4.661895e+00	1.259523e+00	1.0	4.0	5.00	6.000000e+00	9.000000e+00
Food Rating	3493.0	7.522760e+00	1.722721e+00	5.0	6.0	7.00	9.000000e+00	1.000000e+01
Overall Restaurant Rating	3281.0	8.479427e+00	1.287233e+00	6.0	7.0	9.00	1.000000e+01	1.000000e+01
Live Music Rating	2728.0	4.012830e+00	1.009044e+00	1.0	3.0	4.00	5.000000e+00	8.000000e+00
Comedy Gigs Rating	1010.0	2.932673e+00	8.595190e-01	1.0	2.0	3.00	3.000000e+00	6.000000e+00
Value Deals Rating	786.0	3.655216e+00	9.732496e-01	1.0	3.0	4.00	4.000000e+00	7.000000e+00
Live Sports Rating	205.0	3.590244e+00	9.063515e-01	2.0	3.0	4.00	4.000000e+00	6.000000e+00
Ambience	3468.0	6.423010e+00	2.050026e+00	0.0	5.0	7.00	8.000000e+00	1.000000e+01
Lively	3493.0	6.874893e+00	1.847131e+00	0.0	6.0	7.00	8.000000e+00	1.000000e+01
Service	3493.0	4.546808e+00	1.877063e+00	0.0	3.0	5.00	6.000000e+00	1.000000e+01
Comfortablility	3493.0	3.231320e+00	1.993050e+00	0.0	2.0	3.00	5.000000e+00	1.000000e+01
Privacy	3493.0	6.275122e+00	1.895057e+00	0.0	5.0	6.00	8.000000e+00	1.000000e+01

Librerías¶

Lectura del dataset¶

Valores nulos¶

Conclusiones¶

Limpieza de datos¶

Evaluación de interacciones¶

Ridge Estimator¶

XGBoost Estimator¶

	Registration Number	Annual Turnover	Cuisine	City	Restaurant Location	Opening Day of Restaurant	Facebook Popularity Quotient	Endorsed By	Instagram Popularity Quotient	Fire Audit	...	Overall Restaurant Rating	Live Music Rating	Comedy Gigs Rating	Value Deals Rating	Live Sports Rating	Ambience	Lively	Service	Comfortablility	Privacy
0	60001	42000000	indian,irish	Bangalore	Near Business Hub	14-02-2009	84.3	Not Specific	95.8	1	...	10.0	4.0	NaN	NaN	NaN	8.0	8	6	6	6
1	60002	50000000	indian,irish	Indore	Near Party Hub	29-09-2008	85.4	Tier A Celebrity	85.0	1	...	9.0	NaN	4.0	NaN	NaN	5.0	7	7	3	8
2	60003	32500000	tibetan,italian	Chennai	Near Business Hub	30-07-2011	85.0	Tier A Celebrity	68.2	1	...	8.0	3.0	NaN	NaN	NaN	7.0	10	5	2	8
3	60004	110000000	turkish,nigerian	Gurgaon	Near Party Hub	30-11-2008	85.6	Tier A Celebrity	83.6	0	...	9.0	6.0	NaN	NaN	NaN	7.0	7	4	3	5
4	60005	20000000	irish,belgian	Manesar	Near Party Hub	22-02-2010	NaN	Tier A Celebrity	76.8	1	...	6.0	NaN	2.0	NaN	NaN	NaN	6	2	4	6

	% Nulos
Live Sports Rating	94.131119
Value Deals Rating	77.497853
Comedy Gigs Rating	71.085027
Live Music Rating	21.900945
Overall Restaurant Rating	6.069281
Facebook Popularity Quotient	2.834240
Instagram Popularity Quotient	1.603206
Resturant Tier	1.402806
Ambience	0.715717

	value	count
0	Bangalore	553
1	-1	396
2	Noida	324
3	Hyderabad	295
4	Pune	262
5	Chennai	244
6	New Delhi	176
7	Gurgaon	174
8	Mumbai	90
9	Kolkata	88
10	Jaipur	36
11	Mysore	32
12	Lucknow	28
13	chennai	27
14	Greater Noida	24
15	pune	23
16	Navi Mumbai	22
17	Indore	21
18	Chandigarh	21

	Count
tibetan	964
greek	778
thai	549
japanese	475
british	392
turkish	372
irish	358
welsh	345
algerian	305
belgian	280

	Avg Annual Turnover
hawaiian	3.967391e+07
latvian	3.967391e+07
nigerian	3.408635e+07
tibetan	3.332158e+07
greek	3.329949e+07
jewish	3.276838e+07
polish	3.276838e+07
japanese	3.253053e+07
indian	3.215934e+07
turkish	3.160484e+07
italian	3.133813e+07
british	3.003189e+07
irish	2.994832e+07
algerian	2.944426e+07
thai	2.912386e+07
korean	2.907831e+07
peruvian	2.784783e+07
belgian	2.746071e+07
swedish	2.714130e+07
cuban	2.713010e+07
cajun	2.700000e+07
sapnish	2.664966e+07
welsh	2.600725e+07
chinese	2.500629e+07
salvadorian	2.500629e+07